CVE-2026-31406
published 2026-04-06CVE-2026-31406: In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After…
PriorityP336high7.8CVSS 3.1
AVLACLPRLUINSUCHIHAH
EPSS
0.16%
5.6th percentile
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_keepalive_work);
rcu_barrier();
net_complete_free();
net_passive_dec(net);
llist_add(&net->defer_free_list, &defer_free_list);
cleanup_net() [Round 2]
rcu_barrier();
net_complete_free()
kmem_cache_free(net_cachep, net);
nat_keepalive_work()
// on freed net
To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync().
Affected
14 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| debian | linux | < linux 6.19.11-1 (sid) | linux 6.19.11-1 (sid) |
| linux | linux | — | — |
| linux | linux | >= f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae < 32d0f44c2f14d60fe8e920e69a28c11051543ec1 | 32d0f44c2f14d60fe8e920e69a28c11051543ec1 |
| linux | linux | >= f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae < 2255ed6adbc3100d2c4a83abd9d0396d04b87792 | 2255ed6adbc3100d2c4a83abd9d0396d04b87792 |
| linux | linux | >= f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae < 21f2fc49ca6faa393c31da33b8a4e6c41fc84c13 | 21f2fc49ca6faa393c31da33b8a4e6c41fc84c13 |
| linux | linux | >= f531d13bdfe3f4f084aaa8acae2cb0f02295f5ae < daf8e3b253aa760ff9e96c7768a464bc1d6b3c90 | daf8e3b253aa760ff9e96c7768a464bc1d6b3c90 |
| linux | linux_kernel | — | — |
| linux | linux_kernel | — | — |
| linux | linux_kernel | — | — |
| linux | linux_kernel | — | — |
| linux | linux_kernel | — | — |
| linux | linux_kernel | >= 6.11 < 6.12.80 | 6.12.80 |
| linux | linux_kernel | >= 6.13 < 6.18.21 | 6.18.21 |
| linux | linux_kernel | >= 6.19 < 6.19.11 | 6.19.11 |
CVSS provenance
nvdv3.17.8HIGHCVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
vendor_redhat5.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
Red Hat
kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
vendor_redhat·2026-04-06·CVSS 5.5
CVE-2026-31406 [MEDIUM] CWE-825 kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_keepalive_work);
rcu
Debian
CVE-2026-31406: linux - In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix w...
vendor_debian·2026
CVE-2026-31406 [LOW] CVE-2026-31406: linux - In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix w...
In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_
GHSA
GHSA-pfp5-r4vh-w3r6: In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After c
ghsa_unreviewed·2026-04-06
CVE-2026-31406 GHSA-pfp5-r4vh-w3r6: In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After c
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_keepalive_work);
rcu_barrier();
net_complete_free();
net_passive_dec(net);
llist_add(&net->defer_
OSV
CVE-2026-31406: In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After can
osv·2026-04-06
CVE-2026-31406 CVE-2026-31406: In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After can
In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_
No detection rules found.
No public exploits indexed.
Wiz
CVE-2026-31389 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31389 CVE-2026-31389 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31389 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: fix use-after-free on controller registration failure
Make sure to deregister from driver core also in the unlikely event that
per-cpu statistics allocation fails during controller registration to
avoid use-after-free (of driver resources) and unclocked register
accesses.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug
kernel-64k-debug-modules-core
Sourc
Wiz
CVE-2026-23120 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23120 [MEDIUM] CVE-2026-23120 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23120 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
l2tp: avoid one data-race in l2tp_tunnel_del_work()
We should read sk->sk_socket only when dealing with kernel sockets.
syzbot reported the following data-race:
BUG: KCSAN: data-race in l2tp_tunnel_del_work / sk_common_release
write to 0xffff88811c182b20 of 8 bytes by task 5365 on cpu 0:
sk_set_socket include/net/sock.h:2092 [inline]
sock_orphan include/net/sock.h:2118 [inline]
sk_common_release+0xae/0x230 net/core/sock.c:4003
udp_lib_close+0x15/0x20 include/net/udp.h:325
inet_release+0xce/0xf0 net/ipv4/af_inet.c:437
__sock_release net/socket.c:662 [inline]
sock_close+0x6b/0x150 net/socket.c:1455
__fput+0x29b/0x650 fs/file_table.c:468
____fput+0x
Wiz
CVE-2025-68319 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68319 CVE-2025-68319 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68319 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netconsole: Acquire su_mutex before navigating configs hierarchy
There is a race between operations that iterate over the userdata
cg_children list and concurrent add/remove of userdata items through
configfs. The update_userdata() function iterates over the
nt->userdata_group.cg_children list, and count_extradata_entries() also
iterates over this same list to count nodes.
Quoting from Documentation/filesystems/configfs.rst:
A subsystem can navigate the cg_children list and the ci_parent pointer
to see the tree created by the subsystem. This can race with configfs'
management of the hierarchy, so configfs uses the subsystem mutex to
protect modifi
Wiz
CVE-2022-50834 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50834 CVE-2022-50834 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50834 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfc: Fix potential resource leaks
nfc_get_device() take reference for the device, add missing
nfc_put_device() to release it when not need anymore.
Also fix the style warnning by use error EOPNOTSUPP instead of
ENOTSUPP.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-default-devel
kernel-obs-build
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
E
Wiz
CVE-2025-68307 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68307 CVE-2025-68307 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68307 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_xmit_callback(): fix handling of failed transmitted URBs
The driver lacks the cleanup of failed transfers of URBs. This reduces the
number of available URBs per error by 1. This leads to reduced performance
and ultimately to a complete stop of the transmission.
If the sending of a bulk URB fails do proper cleanup:
increase netdev stats
mark the echo_sbk as free
free the driver's context and do accounting
wake the send queue
Source : NVD
## 7
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release
Wiz
CVE-2023-54119 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54119 CVE-2023-54119 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54119 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
inotify: Avoid reporting event with invalid wd
When inotify_freeing_mark() races with inotify_handle_inode_event() it
can happen that inotify_handle_inode_event() sees that i_mark->wd got
already reset to -1 and reports this value to userspace which can
confuse the inotify listener. Avoid the problem by validating that wd is
sensible (and pretend the mark got removed before the event got
generated otherwise).
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile
Wiz
CVE-2026-23292 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23292 CVE-2026-23292 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23292 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: Fix recursive locking in __configfs_open_file()
In flush_write_buffer, &p->frag_sem is acquired and then the loaded store
function is called, which, here, is target_core_item_dbroot_store(). This
function called filp_open(), following which these functions were called
(in reverse order), according to the call trace:
down_read
__configfs_open_file
do_dentry_open
vfs_open
do_open
path_openat
do_filp_open
file_open_name
filp_open
target_core_item_dbroot_store
flush_write_buffer
configfs_write_iter
target_core_item_dbroot_store() tries to validate the new file path by
trying to open the file path provided to it; however, in this case, th
Wiz
CVE-2023-54025 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54025 CVE-2023-54025 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54025 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rsi: Do not configure WoWlan in shutdown hook if not enabled
In case WoWlan was never configured during the operation of the system,
the hw->wiphy->wowlan_config will be NULL. rsi_config_wowlan() checks
whether wowlan_config is non-NULL and if it is not, then WARNs about it.
The warning is valid, as during normal operation the rsi_config_wowlan()
should only ever be called with non-NULL wowlan_config. In shutdown this
rsi_config_wowlan() should only ever be called if WoWlan was configured
before by the user.
Add checks for non-NULL wowlan_config into the shutdown hook. While at it,
check whether the wiphy is also non-NULL before accessing wow
Wiz
CVE-2025-71078 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71078 [HIGH] CVE-2025-71078 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71078 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/64s/slb: Fix SLB multihit issue during SLB preload
On systems using the hash MMU, there is a software SLB preload cache that
mirrors the entries loaded into the hardware SLB buffer. This preload
cache is subject to periodic eviction — typically after every 256 context
switches — to remove old entry.
To optimize performance, the kernel skips switch_mmu_context() in
switch_mm_irqs_off() when the prev and next mm_struct are the same.
However, on hash MMU systems, this can lead to inconsistencies between
the hardware SLB and the software preload cache.
If an SLB entry for a process is evicted from the software cache on one
CPU, and the same pr
Wiz
CVE-2022-50784 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50784 CVE-2022-50784 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50784 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: iwlwifi: mei: fix potential NULL-ptr deref after clone
If cloning the SKB fails, don't try to use it, but rather return
as if we should pass it.
Coverity CID: 1503456
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-tools-libs-devel
kernel-modules-core
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 8
Wiz
CVE-2023-53997 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53997 CVE-2023-53997 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53997 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
thermal: of: fix double-free on unregistration
Since commit 3d439b1a2ad3 ("thermal/core: Alloc-copy-free the thermal
zone parameters structure"), thermal_zone_device_register() allocates
a copy of the tzp argument and frees it when unregistering, so
thermal_of_zone_register() now ends up leaking its original tzp and
double-freeing the tzp copy. Fix this by locating tzp on stack instead.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitatio
Wiz
CVE-2023-54275 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54275 CVE-2023-54275 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54275 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: Fix memory leak in ath11k_peer_rx_frag_setup
crypto_alloc_shash() allocates resources, which should be released by
crypto_free_shash(). When ath11k_peer_find() fails, there has memory
leak. Add missing crypto_free_shash() to fix this.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-devel
linux-oracle-5.15
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Ad
Wiz
CVE-2025-71128 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71128 [MEDIUM] CVE-2025-71128 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71128 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erspan: Initialize options_len before referencing options.
The struct ip_tunnel_info has a flexible array member named
options that is protected by a counted_by(options_len)
attribute.
The compiler will use this information to enforce runtime bounds
checking deployed by FORTIFY_SOURCE string helpers.
As laid out in the GCC documentation, the counter must be
initialized before the first reference to the flexible array
member.
After scanning through the files that use struct ip_tunnel_info
and also refer to options or options_len, it appears the normal
case is to use the ip_tunnel_info_opts_set() helper.
Said helper would initialize options_len pr
Wiz
CVE-2026-23439 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23439 CVE-2026-23439 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23439 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udp_tunnel: fix NULL deref caused by udp_sock_create6 when CONFIG_IPV6=n
When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0
(success) without actually creating a socket. Callers such as
fou_create() then proceed to dereference the uninitialized socket
pointer, resulting in a NULL pointer dereference.
The captured NULL deref crash:
BUG: kernel NULL pointer dereference, address: 0000000000000018
RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764)
[...]
Call Trace: genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114)
genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209)
[..
Wiz
CVE-2023-54271 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54271 CVE-2023-54271 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54271 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
blk-iocost sometimes causes the following crash:
BUG: kernel NULL pointer dereference, address: 00000000000000e0
...
RIP: 0010:_raw_spin_lock+0x17/0x30
Code: be 01 02 00 00 e8 79 38 39 ff 31 d2 89 d0 5d c3 0f 1f 00 0f 1f 44 00 00 55 48 89 e5 65 ff 05 48 d0 34 7e b9 01 00 00 00 31 c0 0f b1 0f 75 02 5d c3 89 c6 e8 ea 04 00 00 5d c3 0f 1f 84 00 00
RSP: 0018:ffffc900023b3d40 EFLAGS: 00010046
RAX: 0000000000000000 RBX: 00000000000000e0 RCX: 0000000000000001
RDX: ffffc900023b3d20 RSI: ffffc900023b3cf0 RDI: 00000000000000e0
RBP: ffffc900023b3d40 R08: ffffc900023b3c10 R09: 00
Wiz
CVE-2022-50750 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50750 CVE-2022-50750 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50750 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/panel/panel-sitronix-st7701: Remove panel on DSI attach failure
In case mipi_dsi_attach() fails, call drm_panel_remove() to
avoid memory leak.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-devel-matched
kernel-rt-64k-debug
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8 Severity LOW Has Fix Adde
Wiz
CVE-2025-68745 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68745 CVE-2025-68745 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68745 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Clear cmds after chip reset
Commit aefed3e5548f ("scsi: qla2xxx: target: Fix offline port handling
and host reset handling") caused two problems:
Commands sent to FW, after chip reset got stuck and never freed as FW
is not going to respond to them anymore.
BUG_ON(cmd->sg_mapped) in qlt_free_cmd(). Commit 26f9ce53817a
("scsi: qla2xxx: Fix missed DMA unmap for aborted commands")
attempted to fix this, but introduced another bug under different
circumstances when two different CPUs were racing to call
qlt_unmap_sg() at the same time: BUG_ON(!valid_dma_direction(dir)) in
dma_unmap_sg_attrs().
So revert "scsi: qla2xxx: Fix missed DMA un
Wiz
CVE-2025-71079 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71079 [MEDIUM] CVE-2025-71079 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71079 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: nfc: fix deadlock between nfc_unregister_device and rfkill_fop_write
A deadlock can occur between nfc_unregister_device() and rfkill_fop_write()
due to lock ordering inversion between device_lock and rfkill_global_mutex.
The problematic lock order is:
Thread A (rfkill_fop_write):
rfkill_fop_write()
mutex_lock(&rfkill_global_mutex)
rfkill_set_block()
nfc_rfkill_set_block()
nfc_dev_down()
device_lock(&dev->dev) dev)
rfkill_unregister()
mutex_lock(&rfkill_global_mutex)
rfkill_global_mutex via rfkill_register) is safe because during
registration the device is not yet in rfkill_list, so no concurrent
rfkill operations can occur on this device.
So
Wiz
CVE-2026-22984 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-22984 [HIGH] CVE-2026-22984 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22984 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: prevent potential out-of-bounds reads in handle_auth_done()
Perform an explicit bounds check on payload_len to avoid a possible
out-of-bounds access in the callout.
[ idryomov: changelog ]
Source : NVD
## 7.1
Score
Published January 23, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-realtime
linux-azure-6.8
Sources
NVD
CBL-Mariner 2.0 Severity HIGH Has Fix Added at: Mar 10,
Wiz
CVE-2023-54213 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54213 CVE-2023-54213 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54213 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
USB: sisusbvga: Add endpoint checks
The syzbot fuzzer was able to provoke a WARNING from the sisusbvga driver:
------------[ cut here ]------------
usb 1-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 1 PID: 26 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504
Modules linked in:
CPU: 1 PID: 26 Comm: kworker/1:1 Not tainted 6.2.0-rc5-syzkaller-00199-g5af6ce704936 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023
Workqueue: usb_hub_wq hub_event
RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504
Code: 7c 24 18 e8 6c 50 80 fb 48 8b 7c 24 18 e8 62 1a 01 ff 41
Wiz
CVE-2025-71142 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71142 [MEDIUM] CVE-2025-71142 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71142 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cpuset: fix warning when disabling remote partition
A warning was triggered as follows:
WARNING: kernel/cgroup/cpuset.c:1651 at remote_partition_disable+0xf7/0x110
RIP: 0010:remote_partition_disable+0xf7/0x110
RSP: 0018:ffffc90001947d88 EFLAGS: 00000206
RAX: 0000000000007fff RBX: ffff888103b6e000 RCX: 0000000000006f40
RDX: 0000000000006f00 RSI: ffffc90001947da8 RDI: ffff888103b6e000
RBP: ffff888103b6e000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: ffff88810b2e2728 R12: ffffc90001947da8
R13: 0000000000000000 R14: ffffc90001947da8 R15: ffff8881081f1c00
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f55c8bbe0b2 C
Wiz
CVE-2023-54253 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54253 CVE-2023-54253 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54253 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: set page extent mapped after read_folio in relocate_one_page
One of the CI runs triggered the following panic
assertion failed: PagePrivate(page) && page->private, in fs/btrfs/subpage.c:229
------------[ cut here ]------------
kernel BUG at fs/btrfs/subpage.c:229!
Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
CPU: 0 PID: 923660 Comm: btrfs Not tainted 6.5.0-rc3+ #1
pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
pc : btrfs_subpage_assert+0xbc/0xf0
lr : btrfs_subpage_assert+0xbc/0xf0
sp : ffff800093213720
x29: ffff800093213720 x28: ffff8000932138b4 x27: 000000000c280000
x26: 00000001b5d00000 x25: 000000000c281000 x24:
Wiz
CVE-2023-54189 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54189 CVE-2023-54189 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54189 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pstore/ram: Add check for kstrdup
Add check for the return value of kstrdup() and return the error
if it fails in order to avoid NULL pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux
kernel-default-base-rebuild
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW No Fix Adde
Wiz
CVE-2026-23085 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23085 [MEDIUM] CVE-2026-23085 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23085 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
irqchip/gic-v3-its: Avoid truncating memory addresses
On 32-bit machines with CONFIG_ARM_LPAE, it is possible for lowmem
allocations to be backed by addresses physical memory above the 32-bit
address limit, as found while experimenting with larger VMSPLIT
configurations.
This caused the qemu virt model to crash in the GICv3 driver, which
allocates the 'itt' object using GFP_KERNEL. Since all memory below
the 4GB physical address limit is in ZONE_DMA in this configuration,
kmalloc() defaults to higher addresses for ZONE_NORMAL, and the
ITS driver stores the physical address in a 32-bit 'unsigned long'
variable.
Change the itt_addr variable to the c
Wiz
CVE-2023-53848 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53848 CVE-2023-53848 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53848 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid5-cache: fix a deadlock in r5l_exit_log()
Commit b13015af94cf ("md/raid5-cache: Clear conf->log after finishing
work") introduce a new problem:
// caller hold reconfig_mutex
r5l_exit_log
flush_work(&log->disable_writeback_work)
r5c_disable_writeback_async
wait_event
/*
* conf->log is not NULL, and mddev_trylock()
* will fail, wait_event() can never pass.
*/
conf->log = NULL
Fix this problem by setting 'config->log' to NULL before wake_up() as it
used to be, so that wait_event() from r5c_disable_writeback_async() can
exist. In the meantime, move forward md_unregister_thread() so that
null-ptr-deref this commit fixed can still be fixed.
So
Wiz
CVE-2023-54090 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54090 CVE-2023-54090 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54090 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ixgbe: Fix panic during XDP_TX with > 64 CPUs
Commit 4fe815850bdc ("ixgbe: let the xdpdrv work with more than 64 cpus")
adds support to allow XDP programs to run on systems with more than
64 CPUs by locking the XDP TX rings and indexing them using cpu % 64
(IXGBE_MAX_XDP_QS).
Upon trying this out patch on a system with more than 64 cores,
the kernel paniced with an array-index-out-of-bounds at the return in
ixgbe_determine_xdp_ring in ixgbe.h, which means ixgbe_determine_xdp_q_idx
was just returning the cpu instead of cpu % IXGBE_MAX_XDP_QS. An example
splat:
## ==========================================================================
UBSAN: arr
Wiz
CVE-2026-23118 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23118 [MEDIUM] CVE-2026-23118 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23118 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rxrpc: Fix data-race warning and potential load/store tearing
Fix the following:
BUG: KCSAN: data-race in rxrpc_peer_keepalive_worker / rxrpc_send_data_packet
which is reporting an issue with the reads and writes to ->last_tx_at in:
conn->peer->last_tx_at = ktime_get_seconds();
and:
keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
The lockless accesses to these to values aren't actually a problem as the
read only needs an approximate time of last transmission for the purposes
of deciding whether or not the transmission of a keepalive packet is
warranted yet.
Also, as ->last_tx_at is a 64-bit value, tearing can occur on a 32-bit
arch.
Wiz
CVE-2026-23046 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23046 CVE-2026-23046 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23046 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
virtio_net: fix device mismatch in devm_kzalloc/devm_kfree
Initial rss_hdr allocation uses virtio_device->device,
but virtnet_set_queues() frees using net_device->device.
This device mismatch causing below devres warning
[ 3788.514041] ------------[ cut here ]------------
[ 3788.514044] WARNING: drivers/base/devres.c:1095 at devm_kfree+0x84/0x98, CPU#16: vdpa/1463
[ 3788.514054] Modules linked in: octep_vdpa virtio_net virtio_vdpa [last unloaded: virtio_vdpa]
[ 3788.514064] CPU: 16 UID: 0 PID: 1463 Comm: vdpa Tainted: G W 6.18.0 #10 PREEMPT
[ 3788.514067] Tainted: [W]=WARN
[ 3788.514069] Hardware name: Marvell CN106XX board (DT)
[ 3788.514071] psta
Wiz
CVE-2026-23054 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23054 CVE-2026-23054 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23054 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: hv_netvsc: reject RSS hash key programming without RX indirection table
RSS configuration requires a valid RX indirection table. When the device
reports a single receive queue, rndis_filter_device_add() does not
allocate an indirection table, accepting RSS hash key updates in this
state leads to a hang.
Fix this by gating netvsc_set_rxfh() on ndc->rx_table_sz and return
-EOPNOTSUPP when the table is absent. This aligns set_rxfh with the device
capabilities and prevents incorrect behavior.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
C
Wiz
CVE-2025-68815 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68815 CVE-2025-68815 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68815 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: ets: Remove drr class from the active list if it changes to strict
Whenever a user issues an ets qdisc change command, transforming a
drr class into a strict one, the ets code isn't checking whether that
class was in the active list and removing it. This means that, if a
user changes a strict class (which was in the active list) back to a drr
one, that class will be added twice to the active list [1].
Doing so with the following commands:
tc qdisc add dev lo root handle 1: ets bands 2 strict 1
tc qdisc add dev lo parent 1:2 handle 20:
tbf rate 8bit burst 100b latency 1s
tc filter add dev lo parent 1: basic classid 1:2
ping -c1 -W0.01 -s
Wiz
CVE-2026-23412 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23412 CVE-2026-23412 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23412 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: bpf: defer hook memory release until rcu readers are done
Yiming Qian reports UaF when concurrent process is dumping hooks via
nfnetlink_hooks:
BUG: KASAN: slab-use-after-free in nfnl_hook_dump_one.isra.0+0xe71/0x10f0
Read of size 8 at addr ffff888003edbf88 by task poc/79
Call Trace: nfnl_hook_dump_one.isra.0+0xe71/0x10f0
netlink_dump+0x554/0x12b0
nfnl_hook_get+0x176/0x230
[..]
Defer release until after concurrent readers have completed.
Source : NVD
Published April 2, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Wiz
CVE-2023-54193 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54193 CVE-2023-54193 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54193 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: cls_api: remove block_cb from driver_list before freeing
Error handler of tcf_block_bind() frees the whole bo->cb_list on error.
However, by that time the flow_block_cb instances are already in the driver
list because driver ndo_setup_tc() callback is called before that up the
call chain in tcf_block_offload_cmd(). This leaves dangling pointers to
freed objects in the list and causes use-after-free 0 . Fix it by also
removing flow_block_cb instances from driver_list before deallocating them.
[ 279.869964] BUG: KASAN: slab-use-after-free in flow_block_cb_setup_simple+0x631/0x7c0
[ 279.871527] Read of size 8 at addr ffff888147e2bf20 by tas
Wiz
CVE-2026-23362 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23362 CVE-2026-23362 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23362 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: bcm: fix locking for bcm_op runtime updates
Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
added a locking for some variables that can be modified at runtime when
updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup().
Usually the RX_SETUP only handles and filters incoming traffic with one
exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is
sent when a specific RTR frame is received. Therefore the rx bcm_op uses
bcm_can_tx() which uses the bcm_tx_lock that was only initialized in
bcm_tx_setup(). Add the missing spin_lock_init() when allocating the
bcm_op in bcm_rx_setup() to handl
Wiz
CVE-2023-53988 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53988 CVE-2023-53988 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53988 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix slab-out-of-bounds read in hdr_delete_de()
Here is a BUG report from syzbot:
BUG: KASAN: slab-out-of-bounds in hdr_delete_de+0xe0/0x150 fs/ntfs3/index.c:806
Read of size 16842960 at addr ffff888079cc0600 by task syz-executor934/3631
Call Trace:
memmove+0x25/0x60 mm/kasan/shadow.c:54
hdr_delete_de+0xe0/0x150 fs/ntfs3/index.c:806
indx_delete_entry+0x74f/0x3670 fs/ntfs3/index.c:2193
ni_remove_name+0x27a/0x980 fs/ntfs3/frecord.c:2910
ntfs_unlink_inode+0x3d4/0x720 fs/ntfs3/inode.c:1712
ntfs_rename+0x41a/0xcb0 fs/ntfs3/namei.c:276
Before using the meta-data in struct INDEX_HDR, we need to
check index header valid or not. Otherwise, the co
Wiz
CVE-2023-54019 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54019 CVE-2023-54019 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54019 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sched/psi: use kernfs polling functions for PSI trigger polling
Destroying psi trigger in cgroup_file_release causes UAF issues when
a cgroup is removed from under a polling process. This is happening
because cgroup removal causes a call to cgroup_file_release while the
actual file is still alive. Destroying the trigger at this point would
also destroy its waitqueue head and if there is still a polling process
on that file accessing the waitqueue, it will step on the freed pointer:
do_select
vfs_poll
do_rmdir
cgroup_rmdir
kernfs_drain_open_files
cgroup_file_release
cgroup_pressure_release
psi_trigger_destroy
wake_up_pollfree(&t->event_wait)
// vfs_
Wiz
CVE-2025-68337 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68337 CVE-2025-68337 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68337 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
jbd2: avoid bug_on in jbd2_journal_get_create_access() when file system corrupted
There's issue when file system corrupted:
------------[ cut here ]------------
kernel BUG at fs/jbd2/transaction.c:1289!
Oops: invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 5 UID: 0 PID: 2031 Comm: mkdir Not tainted 6.18.0-rc1-next
RIP: 0010:jbd2_journal_get_create_access+0x3b6/0x4d0
RSP: 0018:ffff888117aafa30 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff88811a86b000 RCX: ffffffff89a63534
RDX: 1ffff110200ec602 RSI: 0000000000000004 RDI: ffff888100763010
RBP: ffff888100763000 R08: 0000000000000001 R09: ffff888100763028
R10: 0000000000000003 R11: 0000000000000000 R12:
Wiz
CVE-2022-50861 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50861 CVE-2022-50861 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50861 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSD: Finish converting the NFSv2 GETACL result encoder
The xdr_stream conversion inadvertently left some code that set the
page_len of the send buffer. The XDR stream encoders should handle
this automatically now.
This oversight adds garbage past the end of the Reply message.
Clients typically ignore the garbage, but NFSD does not need to send
it, as it leaks stale memory contents onto the wire.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Wiz
CVE-2026-23268 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23268 [HIGH] CVE-2026-23268 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23268 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
apparmor: fix unprivileged local user can do privileged policy management
An unprivileged local user can load, replace, and remove profiles by
opening the apparmorfs interfaces, via a confused deputy attack, by
passing the opened fd to a privileged process, and getting the
privileged process to write to the interface.
This does require a privileged target that can be manipulated to do
the write for the unprivileged process, but once such access is
achieved full policy management is possible and all the possible
implications that implies: removing confinement, DoS of system or
target applications by denying all execution, by-passing the
unprivileged
Wiz
CVE-2023-54226 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54226 CVE-2023-54226 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54226 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
af_unix: Fix data races around sk->sk_shutdown.
KCSAN found a data race around sk->sk_shutdown where unix_release_sock()
and unix_shutdown() update it under unix_state_lock(), OTOH unix_poll()
and unix_dgram_poll() read it locklessly.
We need to annotate the writes and reads with WRITE_ONCE() and READ_ONCE().
BUG: KCSAN: data-race in unix_poll / unix_release_sock
write to 0xffff88800d0f8aec of 1 bytes by task 264 on cpu 0:
unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631
unix_release+0x59/0x80 net/unix/af_unix.c:1042
__sock_release+0x7d/0x170 net/socket.c:653
sock_close+0x19/0x30 net/socket.c:1397
__fput+0x179/0x5e0 fs/file_table.c:321
____fp
Wiz
CVE-2023-53991 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53991 CVE-2023-53991 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53991 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/dpu: Disallow unallocated resources to be returned
In the event that the topology requests resources that have not been
created by the system (because they are typically not represented in
dpu_mdss_cfg ^1), the resource(s) in global_state (in this case DSC
blocks, until their allocation/assignment is being sanity-checked in
"drm/msm/dpu: Reject topologies for which no DSC blocks are available")
remain NULL but will still be returned out of
dpu_rm_get_assigned_resources, where the caller expects to get an array
containing num_blks valid pointers (but instead gets these NULLs).
To prevent this from happening, where null-pointer dereferences
t
Wiz
CVE-2026-23011 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23011 [MEDIUM] CVE-2026-23011 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23011 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv4: ip_gre: make ipgre_header() robust
Analog to commit db5b4e39c4e6 ("ip6_gre: make ip6gre_header() robust")
Over the years, syzbot found many ways to crash the kernel
in ipgre_header() [1].
This involves team or bonding drivers ability to dynamically
change their dev->needed_headroom and/or dev->hard_header_len
In this particular crash mld_newpack() allocated an skb
with a too small reserve/headroom, and by the time mld_sendpack()
was called, syzbot managed to attach an ipgre device.
[1]
skbuff: skb_under_panic: text:ffffffff89ea3cb7 len:2030915468 put:2030915372 head:ffff888058b43000 data:ffff887fdfa6e194 tail:0x120 end:0x6c0 dev:team0
kern
Wiz
CVE-2022-50718 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50718 CVE-2022-50718 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50718 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: fix pci device refcount leak
As comment of pci_get_domain_bus_and_slot() says, it returns
a pci device with refcount increment, when finish using it,
the caller must decrement the reference count by calling
pci_dev_put().
So before returning from amdgpu_device_resume|suspend_display_audio(),
pci_dev_put() is called to avoid refcount leak.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected p
Wiz
CVE-2026-23185 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23185 [HIGH] CVE-2026-23185 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23185 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: iwlwifi: mld: cancel mlo_scan_start_wk
mlo_scan_start_wk is not canceled on disconnection. In fact, it is not
canceled anywhere except in the restart cleanup, where we don't really
have to.
This can cause an init-after-queue issue: if, for example, the work was
queued and then drv_change_interface got executed.
This can also cause use-after-free: if the work is executed after the
vif is freed.
Source : NVD
## 7.8
Score
Published February 14, 2026
Severity HIGH
CNA Score 7.8
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2022-50735 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50735 CVE-2022-50735 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50735 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: do not run mt76u_status_worker if the device is not running
Fix the following NULL pointer dereference avoiding to run
mt76u_status_worker thread if the device is not running yet.
KASAN: null-ptr-deref in range
[0x0000000000000000-0x0000000000000007]
CPU: 0 PID: 98 Comm: kworker/u2:2 Not tainted 5.14.0+ #78 Hardware
name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
Workqueue: mt76 mt76u_tx_status_data
RIP: 0010:mt76x02_mac_fill_tx_status.isra.0+0x82c/0x9e0
Code: c5 48 b8 00 00 00 00 00 fc ff df 80 3c 02 00 0f 85 94 01 00 00
48 b8 00 00 00 00 00 fc ff df 4d 8b 34 24 4c 89 f2 48 c1
Wiz
CVE-2023-54054 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54054 CVE-2023-54054 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54054 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-internal
kernel-rt-64k-debug-core
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 6, 7, 8, 9 Severity HIGH No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Dec 26, 2025
## Get a C
Wiz
CVE-2026-23013 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.0
CVE-2026-23013 [HIGH] CVE-2026-23013 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23013 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: octeon_ep_vf: fix free_irq dev_id mismatch in IRQ rollback
octep_vf_request_irqs() requests MSI-X queue IRQs with dev_id set to
ioq_vector. If request_irq() fails part-way, the rollback loop calls
free_irq() with dev_id set to 'oct', which does not match the original
dev_id and may leave the irqaction registered.
This can keep IRQ handlers alive while ioq_vector is later freed during
unwind/teardown, leading to a use-after-free or crash when an interrupt
fires.
Fix the error path to free IRQs with the same ioq_vector dev_id used
during request_irq().
Source : NVD
## 7.8
Score
Published January 25, 2026
Severity HIGH
CNA Score 7.0
Aff
Wiz
CVE-2025-71099 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71099 [HIGH] CVE-2025-71099 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71099 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/oa: Fix potential UAF in xe_oa_add_config_ioctl()
In xe_oa_add_config_ioctl(), we accessed oa_config->id after dropping
metrics_lock. Since this lock protects the lifetime of oa_config, an
attacker could guess the id and call xe_oa_remove_config_ioctl() with
perfect timing, freeing oa_config before we dereference it, leading to
a potential use-after-free.
Fix this by caching the id in a local variable while holding the lock.
v2: (Matt A)
Dropped mutex_unlock(&oa->metrics_lock) ordering change from
xe_oa_remove_config_ioctl()
(cherry picked from commit 28aeaed130e8e587fd1b73b6d66ca41ccc5a1a31)
Source : NVD
## 7.8
Score
Published Janu
Wiz
CVE-2025-68810 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68810 CVE-2025-68810 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68810 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: Disallow toggling KVM_MEM_GUEST_MEMFD on an existing memslot
Reject attempts to disable KVM_MEM_GUEST_MEMFD on a memslot that was
initially created with a guest_memfd binding, as KVM doesn't support
toggling KVM_MEM_GUEST_MEMFD on existing memslots. KVM prevents enabling
KVM_MEM_GUEST_MEMFD, but doesn't prevent clearing the flag.
Failure to reject the new memslot results in a use-after-free due to KVM
not unbinding from the guest_memfd instance. Unbinding on a FLAGS_ONLY
change is easy enough, and can/will be done as a hardening measure (in
anticipation of KVM supporting dirty logging on guest_memfd at some point),
but fixing the use-after-fre
Wiz
CVE-2026-23125 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23125 [MEDIUM] CVE-2026-23125 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23125 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sctp: move SCTP_CMD_ASSOC_SHKEY right after SCTP_CMD_PEER_INIT
A null-ptr-deref was reported in the SCTP transmit path when SCTP-AUTH key
initialization fails:
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
CPU: 0 PID: 16 Comm: ksoftirqd/0 Tainted: G W 6.6.0 #2
RIP: 0010:sctp_packet_bundle_auth net/sctp/output.c:264 [inline]
RIP: 0010:sctp_packet_append_chunk+0xb36/0x1260 net/sctp/output.c:401
Call Trace:
sctp_packet_transmit_chunk+0x31/0x250 net/sctp/output.c:189
sctp_outq_flush_data+0xa29/0x26d0 net/sctp/outqueue.c:1111
sctp_outq_flush+0xc80/0x1240 net/sctp/outqueue.c:1217
sctp_cmd_interpreter.isra.0+0x19a5/0x62c0 net/sct
Wiz
CVE-2026-23105 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23105 [HIGH] CVE-2026-23105 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23105 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: qfq: Use cl_is_active to determine whether class is active in qfq_rm_from_ag
This is more of a preventive patch to make the code more consistent and
to prevent possible exploits that employ child qlen manipulations on qfq.
use cl_is_active instead of relying on the child qdisc's qlen to determine
class activation.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score 7.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.4
Exploitation Probability (EPSS) N/A
Affec
Wiz
CVE-2023-54206 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54206 CVE-2023-54206 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54206 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: flower: fix filter idr initialization
The cited commit moved idr initialization too early in fl_change() which
allows concurrent users to access the filter that is still being
initialized and is in inconsistent state, which, in turn, can cause NULL
pointer dereference [0]. Since there is no obvious way to fix the ordering
without reverting the whole cited commit, alternative approach taken to
first insert NULL pointer into idr in order to allocate the handle but
still cause fl_get() to return NULL and prevent concurrent users from
seeing the filter while providing miss-to-action infrastructure with valid
handle id early in fl_change().
[
Wiz
CVE-2026-23063 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23063 [MEDIUM] CVE-2026-23063 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23063 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
uacce: ensure safe queue release with state management
put_queue
uacce_queue
stop_queue
put_queue
Queue states are defined as follows:
UACCE_Q_ZOMBIE: Initial state
uacce
start
ioctl
poweroff -f
uacce_fops_release
uacce_remove
uacce_put_queue
uacce_fops_release
ops
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64kb-extra
Wiz
CVE-2026-22988 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22988 [MEDIUM] CVE-2026-22988 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22988 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arp: do not assume dev_hard_header() does not change skb->head
arp_create() is the only dev_hard_header() caller
making assumption about skb->head being unchanged.
A recent commit broke this assumption.
Initialize @arp pointer after dev_hard_header() call.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-tools
kernel-default-vdso
Wiz
CVE-2025-68346 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68346 CVE-2025-68346 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68346 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: dice: fix buffer overflow in detect_stream_formats()
The function detect_stream_formats() reads the stream_count value directly
from a FireWire device without validating it. This can lead to
out-of-bounds writes when a malicious device provides a stream_count value
greater than MAX_STREAMS.
Fix by applying the same validation to both TX and RX stream counts in
detect_stream_formats().
Source : NVD
## 7.8
Score
Published December 24, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabili
Wiz
CVE-2022-50829 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50829 CVE-2022-50829 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50829 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath9k: hif_usb: Fix use-after-free in ath9k_hif_usb_reg_in_cb()
It is possible that skb is freed in ath9k_htc_rx_msg(), then
usb_submit_urb() fails and we try to free skb again. It causes
use-after-free bug. Moreover, if alloc_skb() fails, urb->context becomes
NULL but rx_buf is not freed and there can be a memory leak.
The patch removes unnecessary nskb and makes skb processing more clear: it
is supposed that ath9k_htc_rx_msg() either frees old skb or passes its
managing to another callback function.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Tech
Wiz
CVE-2025-40328 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40328 CVE-2025-40328 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40328 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix potential UAF in smb2_close_cached_fid()
find_or_create_cached_dir() could grab a new reference after kref_put()
had seen the refcount drop to zero but before cfid_list_lock is acquired
in smb2_close_cached_fid(), leading to use-after-free.
Switch to kref_put_lock() so cfid_release() is called with
cfid_list_lock held, closing that gap.
Source : NVD
## 6.4
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation
Wiz
CVE-2023-54245 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54245 CVE-2023-54245 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54245 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: codecs: tx-macro: Fix for KASAN: slab-out-of-bounds
When we run syzkaller we get below Out of Bound.
"KASAN: slab-out-of-bounds Read in regcache_flat_read"
Below is the backtrace of the issue:
dump_backtrace+0x0/0x4c8
show_stack+0x34/0x44
dump_stack_lvl+0xd8/0x118
print_address_description+0x30/0x2d8
kasan_report+0x158/0x198
__asan_report_load4_noabort+0x44/0x50
regcache_flat_read+0x10c/0x110
regcache_read+0xf4/0x180
_regmap_read+0xc4/0x278
_regmap_update_bits+0x130/0x290
regmap_update_bits_base+0xc0/0x15c
snd_soc_component_update_bits+0xa8/0x22c
snd_soc_component_write_field+0x68/0xd4
tx_macro_digital_mute+0xec/0x140
Actually There is no n
Wiz
CVE-2026-23262 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23262 CVE-2026-23262 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23262 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gve: Fix stats report corruption on queue count change
The driver and the NIC share a region in memory for stats reporting.
The NIC calculates its offset into this region based on the total size
of the stats region and the size of the NIC's stats.
When the number of queues is changed, the driver's stats region is
resized. If the queue count is increased, the NIC can write past
the end of the allocated stats region, causing memory corruption.
If the queue count is decreased, there is a gap between the driver
and NIC stats, leading to incorrect stats reporting.
This change fixes the issue by allocating stats region with maximum
size, and the offset
Wiz
CVE-2025-40329 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40329 CVE-2025-40329 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40329 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/sched: Fix deadlock in drm_sched_entity_kill_jobs_cb
The Mesa issue referenced below pointed out a possible deadlock:
[ 1231.611031] Possible interrupt unsafe locking scenario:
[ 1231.611033] CPU0 CPU1
[ 1231.611034] ---- ----
[ 1231.611035] lock(&xa->xa_lock#17);
[ 1231.611038] local_irq_disable();
[ 1231.611039] lock(&fence->lock);
[ 1231.611041] lock(&xa->xa_lock#17);
[ 1231.611044] [ 1231.611045] lock(&fence->lock);
[ 1231.611047]
*** DEADLOCK ***
In this example, CPU0 would be any function accessing job->dependencies
through the xa_* functions that don't disable interrupts (eg:
drm_sched_job_add_dependency(), drm_sched_entity_kill_jobs_
Wiz
CVE-2026-23230 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.8
CVE-2026-23230 [HIGH] CVE-2026-23230 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23230 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: split cached_fid bitfields to avoid shared-byte RMW races
orb $mask, addr
A possible interleaving is:
CPU1: load old byte (has_lease=1, on_list=1)
CPU2: clear both flags (store 0)
CPU1: RMW store (old | IS_OPEN) -> reintroduces cleared bits
To avoid this class of races, convert these flags to separate bool
fields.
Source : NVD
## 5.5
Score
Published February 18, 2026
Severity MEDIUM
CNA Score 8.8
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probability (EPSS) N/A
Wiz
CVE-2025-68282 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68282 CVE-2025-68282 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68282 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: gadget: udc: fix use-after-free in usb_gadget_state_work
A race condition during gadget teardown can lead to a use-after-free
in usb_gadget_state_work(), as reported by KASAN:
BUG: KASAN: invalid-access in sysfs_notify+0x2c/0xd0
Workqueue: events usb_gadget_state_work
The fundamental race occurs because a concurrent event (e.g., an
interrupt) can call usb_gadget_set_state() and schedule gadget->work
at any time during the cleanup process in usb_del_gadget().
Commit 399a45e5237c ("usb: gadget: core: flush gadget workqueue after
device removal") attempted to fix this by moving flush_work() to after
device_del(). However, this does not fully so
Wiz
CVE-2025-68790 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68790 CVE-2025-68790 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68790 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5: Fix double unregister of HCA_PORTS component
Clear hca_devcom_comp in device's private data after unregistering it in
LAG teardown. Otherwise a slightly lagging second pass through
mlx5_unload_one() might try to unregister it again and trip over
use-after-free.
On s390 almost all PCI level recovery events trigger two passes through
mxl5_unload_one() - one through the poll_health() method and one through
mlx5_pci_err_detected() as callback from generic PCI error recovery.
While testing PCI error recovery paths with more kernel debug features
enabled, this issue reproducibly led to kernel panics with the following
call chain:
Unable to han
Wiz
CVE-2026-23414 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23414 CVE-2026-23414 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23414 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tls: Purge async_hold in tls_decrypt_async_wait()
The async_hold queue pins encrypted input skbs while
the AEAD engine references their scatterlist data. Once
tls_decrypt_async_wait() returns, every AEAD operation
has completed and the engine no longer references those
skbs, so they can be freed unconditionally.
A subsequent patch adds batch async decryption to
tls_sw_read_sock(), introducing a new call site that
must drain pending AEAD operations and release held
skbs. Move __skb_queue_purge(&ctx->async_hold) into
tls_decrypt_async_wait() so the purge is centralized
and every caller -- recvmsg's drain path, the -EBUSY
fallback in tls_do_decryption
Wiz
CVE-2025-71234 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71234 [HIGH] CVE-2025-71234 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71234 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtl8xxxu: fix slab-out-of-bounds in rtl8xxxu_sta_add
The driver does not set hw->sta_data_size, which causes mac80211 to
allocate insufficient space for driver private station data in
__sta_info_alloc(). When rtl8xxxu_sta_add() accesses members of
struct rtl8xxxu_sta_info through sta->drv_priv, this results in a
slab-out-of-bounds write.
KASAN report on RISC-V (VisionFive 2) with RTL8192EU adapter:
BUG: KASAN: slab-out-of-bounds in rtl8xxxu_sta_add+0x31c/0x346
Write of size 8 at addr ffffffd6d3e9ae88 by task kworker/u16:0/12
Set hw->sta_data_size to sizeof(struct rtl8xxxu_sta_info) during
probe, similar to how hw->vif_data_size is configure
Wiz
CVE-2026-23367 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23367 CVE-2026-23367 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23367 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: radiotap: reject radiotap with unknown bits
The radiotap parser is currently only used with the radiotap
namespace (not with vendor namespaces), but if the undefined
field 18 is used, the alignment/size is unknown as well. In
this case, iterator->_next_ns_data isn't initialized (it's
only set for skipping vendor namespaces), and syzbot points
out that we later compare against this uninitialized value.
Fix this by moving the rejection of unknown radiotap fields
down to after the in-namespace lookup, so it will really use
iterator->_next_ns_data only for vendor namespaces, even in
case undefined fields are present.
Source : NVD
## 7.1
Scor
Wiz
CVE-2025-68188 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68188 CVE-2025-68188 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68188 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tcp: use dst_dev_rcu() in tcp_fastopen_active_disable_ofo_check()
Use RCU to avoid a pair of atomic operations and a potential
UAF on dst_dev()->flags.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek64k-modules
linux-aws
Sources
NVD
Container-Optimized OS Has Fix Added at: Jan 07, 2026
Debian 11, 12 No Fix Added at: Dec 17, 2025
Wiz
CVE-2022-50701 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50701 CVE-2022-50701 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50701 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7921s: fix slab-out-of-bounds access in sdio host
SDIO may need addtional 511 bytes to align bus operation. If the tailroom
of this skb is not big enough, we would access invalid memory region.
For low level operation, increase skb size to keep valid memory access in
SDIO host.
Error message:
[69.951] BUG: KASAN: slab-out-of-bounds in sg_copy_buffer+0xe9/0x1a0
[69.951] Read of size 64 at addr ffff88811c9cf000 by task kworker/u16:7/451
[69.951] CPU: 4 PID: 451 Comm: kworker/u16:7 Tainted: G W OE 6.1.0-rc5 #1
[69.951] Workqueue: kvub300c vub300_cmndwork_thread [vub300]
[69.951] Call Trace:
[69.951] [69.952] dump_stack_lvl+0x49/0x63
[69.
Wiz
CVE-2025-71093 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71093 [HIGH] CVE-2025-71093 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71093 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
e1000: fix OOB in e1000_tbi_should_accept()
In e1000_tbi_should_accept() we read the last byte of the frame via
'data[length - 1]' to evaluate the TBI workaround. If the descriptor-
reported length is zero or larger than the actual RX buffer size, this
read goes out of bounds and can hit unrelated slab objects. The issue
is observed from the NAPI receive path (e1000_clean_rx_irq):
BUG: KASAN: slab-out-of-bounds in e1000_tbi_should_accept+0x610/0x790
Read of size 1 at addr ffff888014114e54 by task sshd/363
CPU: 0 PID: 363 Comm: sshd Not tainted 5.18.0-rc1 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-pre
Wiz
CVE-2026-23158 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23158 [HIGH] CVE-2026-23158 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23158 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gpio: virtuser: fix UAF in configfs release path
The gpio-virtuser configfs release path uses guard(mutex) to protect
the device structure. However, the device is freed before the guard
cleanup runs, causing mutex_unlock() to operate on freed memory.
Specifically, gpio_virtuser_device_config_group_release() destroys
the mutex and frees the device while still inside the guard(mutex)
scope. When the function returns, the guard cleanup invokes
mutex_unlock(&dev->lock), resulting in a slab use-after-free.
Limit the mutex lifetime by using a scoped_guard() only around the
activation check, so that the lock is released before mutex_destroy()
and kfree()
Wiz
CVE-2025-68239 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68239 CVE-2025-68239 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68239 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
binfmt_misc: restore write access before closing files opened by open_exec()
bm_register_write() opens an executable file using open_exec(), which
internally calls do_open_execat() and denies write access on the file to
avoid modification while it is being executed.
However, when an error occurs, bm_register_write() closes the file using
filp_close() directly. This does not restore the write permission, which
may cause subsequent write operations on the same file to fail.
Fix this by calling exe_file_allow_write_access() before filp_close() to
restore the write permission properly.
Source : NVD
## 5.7
Score
Published December 16, 2025
Sever
Wiz
CVE-2026-23254 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23254 CVE-2026-23254 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23254 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: gro: fix outer network offset
encapsulation
Due to the above, in the problematic scenarios, udp4_gro_complete() uses
the wrong network offset (inner instead of outer) to compute the outer
UDP header pseudo checksum, leading to csum validation errors later on
in packet processing.
Address the issue always clearing the encapsulation flag at GRO completion
time. Such flag will be set again as needed for encapsulated packets by
udp_gro_complete().
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/
Wiz
CVE-2022-50866 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50866 CVE-2022-50866 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50866 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: pxa: fix null-pointer dereference in filter()
kasprintf() would return NULL pointer when kmalloc() fail to allocate.
Need to check the return pointer before calling strcmp().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 20.3
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-devel
bpftool
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 8 Severity ME
Wiz
CVE-2023-54102 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54102 CVE-2023-54102 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54102 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: lpfc: Prevent lpfc_debugfs_lockstat_write() buffer overflow
A static code analysis tool flagged the possibility of buffer overflow when
using copy_from_user() for a debugfs entry.
Currently, it is possible that copy_from_user() copies more bytes than what
would fit in the mybuf char array. Add a min() restriction check between
sizeof(mybuf) - 1 and nbytes passed from the userspace buffer to protect
against buffer overflow.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Prob
Wiz
CVE-2025-71182 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71182 [MEDIUM] CVE-2025-71182 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71182 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: j1939: make j1939_session_activate() fail if device is no longer registered
syzbot is still reporting
unregister_netdevice: waiting for vcan0 to become free. Usage count = 2
even after commit 93a27b5891b8 ("can: j1939: add missing calls in
NETDEV_UNREGISTER notification handler") was added. A debug printk() patch
found that j1939_session_activate() can succeed even after
j1939_cancel_active_session() from j1939_netdev_notify(NETDEV_UNREGISTER)
has completed.
Since j1939_cancel_active_session() is processed with the session list lock
held, checking ndev->reg_state in j1939_session_activate() with the session
list lock held can reliably close
Wiz
CVE-2023-54096 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54096 CVE-2023-54096 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54096 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
soundwire: fix enumeration completion
The soundwire subsystem uses two completion structures that allow
drivers to wait for soundwire device to become enumerated on the bus and
initialised by their drivers, respectively.
The code implementing the signalling is currently broken as it does not
signal all current and future waiters and also uses the wrong
reinitialisation function, which can potentially lead to memory
corruption if there are still waiters on the queue.
Not signalling future waiters specifically breaks sound card probe
deferrals as codec drivers can not tell that the soundwire device is
already attached when being reprobed. Some codec
Wiz
CVE-2023-54247 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54247 CVE-2023-54247 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54247 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Silence a warning in btf_type_id_size()
syzbot reported a warning in [1] with the following stacktrace:
WARNING: CPU: 0 PID: 5005 at kernel/bpf/btf.c:1988 btf_type_id_size+0x2d9/0x9d0 kernel/bpf/btf.c:1988
...
RIP: 0010:btf_type_id_size+0x2d9/0x9d0 kernel/bpf/btf.c:1988
...
Call Trace: map_check_btf kernel/bpf/syscall.c:1024 [inline]
map_create+0x1157/0x1860 kernel/bpf/syscall.c:1198
__sys_bpf+0x127f/0x5420 kernel/bpf/syscall.c:5040
__do_sys_bpf kernel/bpf/syscall.c:5162 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5160 [inline]
__x64_sys_bpf+0x79/0xc0 kernel/bpf/syscall.c:5160
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x39
Wiz
CVE-2025-68295 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68295 CVE-2025-68295 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68295 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix memory leak in cifs_construct_tcon()
When having a multiuser mount with domain= specified and using
cifscreds, cifs_set_cifscreds() will end up setting @ctx->domainname,
so it needs to be freed before leaving cifs_construct_tcon().
This fixes the following memory leak reported by kmemleak:
mount.cifs //srv/share /mnt -o domain=ZELDA,multiuser,...
su - testuser
cifscreds add -d ZELDA -u testuser
...
ls /mnt/1
...
umount /mnt
echo scan > /sys/kernel/debug/kmemleak
cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff8881203c3f08 (size 8):
comm "ls", pid 5060, jiffies 4307222943
hex dump (first 8 bytes):
5a 45 4c 44 41 00 cc cc Z
Wiz
CVE-2026-23374 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23374 CVE-2026-23374 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23374 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blktrace: fix __this_cpu_read/write in preemptible context
tracing_record_cmdline() internally uses __this_cpu_read() and
__this_cpu_write() on the per-CPU variable trace_cmdline_save, and
trace_save_cmdline() explicitly asserts preemption is disabled via
lockdep_assert_preemption_disabled(). These operations are only safe
when preemption is off, as they were designed to be called from the
scheduler context (probe_wakeup_sched_switch() / probe_wakeup()).
__blk_add_trace() was calling tracing_record_cmdline(current) early in
the blk_tracer path, before ring buffer reservation, from process
context where preemption is fully enabled. This triggers the
Wiz
CVE-2025-40332 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40332 CVE-2025-40332 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40332 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdkfd: Fix mmap write lock not release
If mmap write lock is taken while draining retry fault, mmap write lock
is not released because svm_range_restore_pages calls mmap_read_unlock
then returns. This causes deadlock and system hangs later because mmap
read or write lock cannot be taken.
Downgrade mmap write lock to read lock if draining retry fault fix this
bug.
Source : NVD
## 5.1
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6
Wiz
CVE-2025-71194 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71194 CVE-2025-71194 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71194 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix deadlock in wait_current_trans() due to ignored transaction type
When wait_current_trans() is called during start_transaction(), it
currently waits for a blocked transaction without considering whether
the given transaction type actually needs to wait for that particular
transaction state. The btrfs_blocked_trans_types[] array already defines
which transaction types should wait for which transaction states, but
this check was missing in wait_current_trans().
This can lead to a deadlock scenario involving two transactions and
pending ordered extents:
Transaction A is in TRANS_STATE_COMMIT_DOING state
A worker processing an ordered exten
Wiz
CVE-2025-68207 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68207 CVE-2025-68207 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68207 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/guc: Synchronize Dead CT worker with unbind
Cancel and wait for any Dead CT worker to complete before continuing
with device unbinding. Else the worker will end up using resources freed
by the undind operation.
(cherry picked from commit 492671339114e376aaa38626d637a2751cdef263)
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-docs
kernel-obs-build
Sources
NVD
Wiz
CVE-2026-23258 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23258 CVE-2026-23258 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23258 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: liquidio: Initialize netdev pointer before queue setup
In setup_nic_devices(), the netdev is allocated using alloc_etherdev_mq().
However, the pointer to this structure is stored in oct->props[i].netdev
only after the calls to netif_set_real_num_rx_queues() and
netif_set_real_num_tx_queues().
If either of these functions fails, setup_nic_devices() returns an error
without freeing the allocated netdev. Since oct->props[i].netdev is still
NULL at this point, the cleanup function liquidio_destroy_nic_device()
will fail to find and free the netdev, resulting in a memory leak.
Fix this by initializing oct->props[i].netdev before calling the queue
Wiz
CVE-2023-53855 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53855 CVE-2023-53855 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53855 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: dsa: ocelot: call dsa_tag_8021q_unregister() under rtnl_lock() on driver remove
When the tagging protocol in current use is "ocelot-8021q" and we unbind
the driver, we see this splat:
$ echo '0000:00:00.2' > /sys/bus/pci/drivers/fsl_enetc/unbind
mscc_felix 0000:00:00.5 swp0: left promiscuous mode
sja1105 spi2.0: Link is Down
DSA: tree 1 torn down
mscc_felix 0000:00:00.5 swp2: left promiscuous mode
sja1105 spi2.2: Link is Down
DSA: tree 3 torn down
fsl_enetc 0000:00:00.2 eno2: left promiscuous mode
mscc_felix 0000:00:00.5: Link is Down
------------[ cut here ]------------
RTNL: assertion failed at net/dsa/tag_8021q.c (409)
WARNING: CPU: 1 PID:
Wiz
CVE-2022-50777 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50777 CVE-2022-50777 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50777 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: phy: xgmiitorgmii: Fix refcount leak in xgmiitorgmii_probe
of_phy_find_device() return device node with refcount incremented.
Call put_device() to relese it when not needed anymore.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gkeop
kernel-default-man
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red H
Wiz
CVE-2025-68264 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68264 CVE-2025-68264 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68264 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: refresh inline data size before write operations
The cached ei->i_inline_size can become stale between the initial size
check and when ext4_update_inline_data()/ext4_create_inline_data() use
it. Although ext4_get_max_inline_size() reads the correct value at the
time of the check, concurrent xattr operations can modify i_inline_size
before ext4_write_lock_xattr() is acquired.
This causes ext4_update_inline_data() and ext4_create_inline_data() to
work with stale capacity values, leading to a BUG_ON() crash in
ext4_write_inline_data():
kernel BUG at fs/ext4/inline.c:1331!
BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
The race window:
ext4
Wiz
CVE-2026-23417 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23417 CVE-2026-23417 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23417 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix constant blinding for PROBE_MEM32 stores
BPF_ST | BPF_PROBE_MEM32 immediate stores are not handled by
bpf_jit_blind_insn(), allowing user-controlled 32-bit immediates to
survive unblinded into JIT-compiled native code when bpf_jit_harden >= 1.
The root cause is that convert_ctx_accesses() rewrites BPF_ST|BPF_MEM
to BPF_ST|BPF_PROBE_MEM32 for arena pointer stores during verification,
before bpf_jit_blind_constants() runs during JIT compilation. The
blinding switch only matches BPF_ST|BPF_MEM (mode 0x60), not
BPF_ST|BPF_PROBE_MEM32 (mode 0xa0). The instruction falls through
unblinded.
Add BPF_ST|BPF_PROBE_MEM32 cases to bpf_jit_blind_insn()
Wiz
CVE-2023-54201 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54201 CVE-2023-54201 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54201 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/efa: Fix wrong resources deallocation order
When trying to destroy QP or CQ, we first decrease the refcount and
potentially free memory regions allocated for the object and then
request the device to destroy the object. If the device fails, the
object isn't fully destroyed so the user/IB core can try to destroy the
object again which will lead to underflow when trying to decrease an
already zeroed refcount.
Deallocate resources in reverse order of allocating them to safely free
them.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA
Wiz
CVE-2023-54034 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54034 CVE-2023-54034 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54034 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommufd: Make sure to zero vfio_iommu_type1_info before copying to user
Missed a zero initialization here. Most of the struct is filled with
a copy_from_user(), however minsz for that copy is smaller than the
actual struct by 8 bytes, thus we don't fill the padding.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-core
kernel-zfcpdump-modules-extra
Sources
NV
Wiz
CVE-2023-54185 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54185 CVE-2023-54185 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54185 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: remove BUG_ON()'s in add_new_free_space()
At add_new_free_space() we have these BUG_ON()'s that are there to deal
with any failure to add free space to the in memory free space cache.
Such failures are mostly -ENOMEM that should be very rare. However there's
no need to have these BUG_ON()'s, we can just return any error to the
caller and all callers and their upper call chain are already dealing with
errors.
So just make add_new_free_space() return any errors, while removing the
BUG_ON()'s, and returning the total amount of added free space to an
optional u64 pointer argument.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affect
Wiz
CVE-2025-68797 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68797 CVE-2025-68797 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68797 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
char: applicom: fix NULL pointer dereference in ac_ioctl
Discovered by Atuin - Automated Vulnerability Discovery Engine.
In ac_ioctl, the validation of IndexCard and the check for a valid
RamIO pointer are skipped when cmd is 6. However, the function
unconditionally executes readb(apbs[IndexCard].RamIO + VERS) at the
end.
If cmd is 6, IndexCard may reference a board that does not exist
(where RamIO is NULL), leading to a NULL pointer dereference.
Fix this by skipping the readb access when cmd is 6, as this
command is a global information query and does not target a specific
board context.
Source : NVD
Published January 13, 2026
CNA Score N/A
Wiz
CVE-2025-68183 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68183 CVE-2025-68183 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68183 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ima: don't clear IMA_DIGSIG flag when setting or removing non-IMA xattr
Currently when both IMA and EVM are in fix mode, the IMA signature will
be reset to IMA hash if a program first stores IMA signature in
security.ima and then writes/removes some other security xattr for the
file.
For example, on Fedora, after booting the kernel with "ima_appraise=fix
evm=fix ima_policy=appraise_tcb" and installing rpm-plugin-ima,
installing/reinstalling a package will not make good reference IMA
signature generated. Instead IMA hash is generated,
# getfattr -m - -d -e hex /usr/bin/bash
# file: usr/bin/bash
security.ima=0x0404...
This happens because when sett
Wiz
CVE-2022-50778 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50778 CVE-2022-50778 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50778 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fortify: Fix __compiletime_strlen() under UBSAN_BOUNDS_LOCAL
With CONFIG_FORTIFY=y and CONFIG_UBSAN_LOCAL_BOUNDS=y enabled, we observe
a runtime panic while running Android's Compatibility Test Suite's (CTS)
android.hardware.input.cts.tests. This is stemming from a strlen()
call in hidinput_allocate().
__compiletime_strlen() is implemented in terms of __builtin_object_size(),
then does an array access to check for NUL-termination. A quirk of
__builtin_object_size() is that for strings whose values are runtime
dependent, __builtin_object_size(str, 1 or 0) returns the maximum size
of possible values when those sizes are determinable at compile time.
Wiz
CVE-2025-68776 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68776 CVE-2025-68776 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68776 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/hsr: fix NULL pointer dereference in prp_get_untagged_frame()
prp_get_untagged_frame() calls __pskb_copy() to create frame->skb_std
but doesn't check if the allocation failed. If __pskb_copy() returns
NULL, skb_clone() is called with a NULL pointer, causing a crash:
Oops: general protection fault, probably for non-canonical address 0xdffffc000000000f: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000078-0x000000000000007f]
CPU: 0 UID: 0 PID: 5625 Comm: syz.1.18 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:skb_clone+0xd7
Wiz
CVE-2023-54295 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54295 CVE-2023-54295 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54295 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mtd: spi-nor: Fix shift-out-of-bounds in spi_nor_set_erase_type
spi_nor_set_erase_type() was used either to set or to mask out an erase
type. When we used it to mask out an erase type a shift-out-of-bounds
was hit:
UBSAN: shift-out-of-bounds in drivers/mtd/spi-nor/core.c:2237:24
shift exponent 4294967295 is too large for 32-bit type 'int'
The setting of the size_{shift, mask} and of the opcode are unnecessary
when the erase size is zero, as throughout the code just the erase size
is considered to determine whether an erase type is supported or not.
Setting the opcode to 0xFF was wrong too as nobody guarantees that 0xFF
is an unused opcode. Thus whe
Wiz
CVE-2023-54237 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54237 CVE-2023-54237 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54237 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/smc: fix potential panic dues to unprotected smc_llc_srv_add_link()
There is a certain chance to trigger the following panic:
PID: 5900 TASK: ffff88c1c8af4100 CPU: 1 COMMAND: "kworker/1:48"
#0 [ffff9456c1cc79a0] machine_kexec at ffffffff870665b7
#1 [ffff9456c1cc79f0] __crash_kexec at ffffffff871b4c7a
#2 [ffff9456c1cc7ab0] crash_kexec at ffffffff871b5b60
#3 [ffff9456c1cc7ac0] oops_end at ffffffff87026ce7
#4 [ffff9456c1cc7ae0] page_fault_oops at ffffffff87075715
#5 [ffff9456c1cc7b58] exc_page_fault at ffffffff87ad0654
#6 [ffff9456c1cc7b80] asm_exc_page_fault at ffffffff87c00b62
[exception RIP: ib_alloc_mr+19]
RIP: ffffffffc0c9cce3 RSP: ffff9456c1
Wiz
CVE-2026-23030 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23030 CVE-2026-23030 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23030 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
phy: rockchip: inno-usb2: Fix a double free bug in rockchip_usb2phy_probe()
The for_each_available_child_of_node() calls of_node_put() to
release child_np in each success loop. After breaking from the
loop with the child_np has been released, the code will jump to
the put_child label and will call the of_node_put() again if the
devm_request_threaded_irq() fails. These cause a double free bug.
Fix by returning directly to avoid the duplicate of_node_put().
Source : NVD
Published January 31, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due
Wiz
CVE-2025-71150 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71150 [MEDIUM] CVE-2025-71150 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71150 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksmbd: Fix refcount leak when invalid session is found on session lookup
When a session is found but its state is not SMB2_SESSION_VALID, It
indicates that no valid session was found, but it is missing to decrement
the reference count acquired by the session lookup, which results in
a reference count leak. This patch fixes the issue by explicitly calling
ksmbd_user_session_put to release the reference to the session.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date
Wiz
CVE-2023-54264 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54264 CVE-2023-54264 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54264 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/sysv: Null check to prevent null-ptr-deref bug
sb_getblk(inode->i_sb, parent) return a null ptr and taking lock on
that leads to the null-ptr-deref bug.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64kb-extra
linux-azure-5.4
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6 Severity LOW No Fix Add
Wiz
CVE-2026-23251 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23251 CVE-2026-23251 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23251 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: only call xf{array,blob}_destroy if we have a valid pointer
Only call the xfarray and xfblob destructor if we have a valid pointer,
and be sure to null out that pointer afterwards. Note that this patch
fixes a large number of commits, most of which were merged between 6.9
and 6.10.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uki-virt-addons
kernel-zfcpdump-devel
Wiz
CVE-2025-68785 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68785 CVE-2025-68785 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68785 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: openvswitch: fix middle attribute validation in push_nsh() action
The push_nsh() action structure looks like this:
OVS_ACTION_ATTR_PUSH_NSH(OVS_KEY_ATTR_NSH(OVS_NSH_KEY_ATTR_BASE,...))
The outermost OVS_ACTION_ATTR_PUSH_NSH attribute is OK'ed by the
nla_for_each_nested() inside __ovs_nla_copy_actions(). The innermost
OVS_NSH_KEY_ATTR_BASE/MD1/MD2 are OK'ed by the nla_for_each_nested()
inside nsh_key_put_from_nlattr(). But nothing checks if the attribute
in the middle is OK. We don't even check that this attribute is the
OVS_KEY_ATTR_NSH. We just do a double unwrap with a pair of nla_data()
calls - first time directly while calling validate_pu
Wiz
CVE-2025-33220 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-33220 [HIGH] CVE-2025-33220 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-33220 :
Linux Ubuntu vulnerability analysis and mitigation
NVIDIA vGPU software contains a vulnerability in the Virtual GPU Manager, where a malicious guest could cause heap memory access after the memory is freed. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, data tampering, denial of service, or information disclosure.
Source : NVD
## 7.8
Score
Published January 28, 2026
Severity HIGH
CNA Score 7.8
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
nvidia-graphics-drivers-580
nvidia-graphics-drivers-580-server
So
Wiz
CVE-2026-23440 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23440 CVE-2026-23440 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23440 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Fix race condition during IPSec ESN update
In IPSec full offload mode, the device reports an ESN (Extended
Sequence Number) wrap event to the driver. The driver validates this
event by querying the IPSec ASO and checking that the esn_event_arm
field is 0x0, which indicates an event has occurred. After handling
the event, the driver must re-arm the context by setting esn_event_arm
back to 0x1.
A race condition exists in this handling path. After validating the
event, the driver calls mlx5_accel_esp_modify_xfrm() to update the
kernel's xfrm state. This function temporarily releases and
re-acquires the xfrm state lock.
So, need to acknowle
Wiz
CVE-2025-68186 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68186 CVE-2025-68186 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68186 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ring-buffer: Do not warn in ring_buffer_map_get_reader() when reader catches up
The function ring_buffer_map_get_reader() is a bit more strict than the
other get reader functions, and except for certain situations the
rb_get_reader_page() should not return NULL. If it does, it triggers a
warning.
This warning was triggering but after looking at why, it was because
another acceptable situation was happening and it wasn't checked for.
If the reader catches up to the writer and there's still data to be read
on the reader page, then the rb_get_reader_page() will return NULL as
there's no new page to get.
In this situation, the reader page should not
Wiz
CVE-2022-50724 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50724 CVE-2022-50724 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50724 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regulator: core: fix resource leak in regulator_register()
I got some resource leak reports while doing fault injection test:
OF: ERROR: memory leak, expected refcount 1 instead of 100,
of_node_get()/of_node_put() unbalanced - destroy cset entry:
attach overlay node /i2c/pmic@64/regulators/buck1
unreferenced object 0xffff88810deea000 (size 512):
comm "490-i2c-rt5190a", pid 253, jiffies 4294859840 (age 5061.046s)
hex dump (first 32 bytes):
00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N..........
ff ff ff ff ff ff ff ff a0 1e 00 a1 ff ff ff ff ................
backtrace:
[] kmalloc_trace+0x21/0x110
[] device_private_init+0x32/0xd0
[] device_
Wiz
CVE-2026-23198 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23198 [HIGH] CVE-2026-23198 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23198 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: Don't clobber irqfd routing type when deassigning irqfd
When deassigning a KVM_IRQFD, don't clobber the irqfd's copy of the IRQ's
routing entry as doing so breaks kvm_arch_irq_bypass_del_producer() on x86
and arm64, which explicitly look for KVM_IRQ_ROUTING_MSI. Instead, to
handle a concurrent routing update, verify that the irqfd is still active
before consuming the routing information. As evidenced by the x86 and
arm64 bugs, and another bug in kvm_arch_update_irqfd_routing() (see below),
clobbering the entry type without notifying arch code is surprising and
error prone.
As a bonus, checking that the irqfd is active provides a convenient
loc
Wiz
CVE-2026-23144 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23144 [MEDIUM] CVE-2026-23144 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23144 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/damon/sysfs: cleanup attrs subdirs on context dir setup failure
When a context DAMON sysfs directory setup is failed after setup of attrs/
directory, subdirectories of attrs/ directory are not cleaned up. As a
result, DAMON sysfs interface is nearly broken until the system reboots,
and the memory for the unremoved directory is leaked.
Cleanup the directories under such failures.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percen
Wiz
CVE-2025-71136 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71136 [HIGH] CVE-2025-71136 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71136 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: adv7842: Avoid possible out-of-bounds array accesses in adv7842_cp_log_status()
It's possible for cp_read() and hdmi_read() to return -EIO. Those
values are further used as indexes for accessing arrays.
Fix that by checking return values where it's needed.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Source : NVD
## 7.1
Score
Published January 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
A
Wiz
CVE-2026-23076 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23076 [HIGH] CVE-2026-23076 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23076 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: ctxfi: Fix potential OOB access in audio mixer handling
In the audio mixer handling code of ctxfi driver, the conf field is
used as a kind of loop index, and it's referred in the index callbacks
(amixer_index() and sum_index()).
As spotted recently by fuzzers, the current code causes OOB access at
those functions.
| UBSAN: array-index-out-of-bounds in /build/reproducible-path/linux-6.17.8/sound/pci/ctxfi/ctamixer.c:347:48
| index 8 is out of range for type 'unsigned char [8]'
After the analysis, the cause was found to be the lack of the proper
(re-)initialization of conj field.
This patch addresses those OOB accesses by adding the proper
in
Wiz
CVE-2023-54135 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54135 CVE-2023-54135 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54135 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
maple_tree: fix potential out-of-bounds access in mas_wr_end_piv()
Check the write offset end bounds before using it as the offset into the
pivot array. This avoids a possible out-of-bounds access on the pivot
array if the write extends to the last slot in the node, in which case the
node maximum should be used as the end pivot.
akpm: this doesn't affect any current callers, but new users of mapletree
may encounter this problem if backported into earlier kernels, so let's
fix it in -stable kernels in case of this.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has
Wiz
CVE-2022-50738 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50738 CVE-2022-50738 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50738 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vhost-vdpa: fix an iotlb memory leak
Before commit 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB")
we called vhost_vdpa_iotlb_unmap(v, iotlb, 0ULL, 0ULL - 1) during
release to free all the resources allocated when processing user IOTLB
messages through vhost_vdpa_process_iotlb_update().
That commit changed the handling of IOTLB a bit, and we accidentally
removed some code called during the release.
We partially fixed this with commit 037d4305569a ("vhost-vdpa: call
vhost_vdpa_cleanup during the release") but a potential memory leak is
still there as showed by kmemleak if the application does not send
VHOST_IOTLB_INVALIDATE or crashes:
unre
Wiz
CVE-2025-40339 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40339 CVE-2025-40339 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40339 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: fix nullptr err of vm_handle_moved
If a amdgpu_bo_va is fpriv->prt_va, the bo of this one is always NULL.
So, such kind of amdgpu_bo_va should be updated separately before
amdgpu_vm_handle_moved.
Source : NVD
## 5.1
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gke
linux-oracle-5.4
Sources
NVD
Debian 11, 12 No Fix Added at: Dec 09, 2025
De
Wiz
CVE-2023-54126 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54126 CVE-2023-54126 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54126 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: safexcel - Cleanup ring IRQ workqueues on load failure
A failure loading the safexcel driver results in the following warning
on boot, because the IRQ affinity has not been correctly cleaned up.
Ensure we clean up the affinity and workqueues on a failure to load the
driver.
crypto-safexcel: probe of f2800000.crypto failed with error -2
------------[ cut here ]------------
WARNING: CPU: 1 PID: 232 at kernel/irq/manage.c:1913 free_irq+0x300/0x340
Modules linked in: hwmon mdio_i2c crypto_safexcel(+) md5 sha256_generic libsha256 authenc libdes omap_rng rng_core nft_masq nft_nat nft_chain_nat nf_nat nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_i
Wiz
CVE-2025-71193 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71193 CVE-2025-71193 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71193 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
phy: qcom-qusb2: Fix NULL pointer dereference on early suspend
Enabling runtime PM before attaching the QPHY instance as driver data
can lead to a NULL pointer dereference in runtime PM callbacks that
expect valid driver data. There is a small window where the suspend
callback may run after PM runtime enabling and before runtime forbid.
This causes a sporadic crash during boot:
Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a1
[...]
CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.7+ #116 PREEMPT
Workqueue: pm pm_runtime_work
pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : qusb2_phy_ru
Wiz
CVE-2026-23236 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.3
CVE-2026-23236 [HIGH] CVE-2026-23236 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23236 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fbdev: smscufx: properly copy ioctl memory to kernelspace
The UFX_IOCTL_REPORT_DAMAGE ioctl does not properly copy data from
userspace to kernelspace, and instead directly references the memory,
which can cause problems if invalid data is passed from userspace. Fix
this all up by correctly copying the memory before accessing it within
the kernel.
Source : NVD
## 5.5
Score
Published March 4, 2026
Severity MEDIUM
CNA Score 7.3
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.9
Exploitation Probabilit
Wiz
CVE-2025-71235 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71235 [MEDIUM] CVE-2025-71235 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71235 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Delay module unload while fabric scan in progress
System crash seen during load/unload test in a loop.
[105954.384919] RBP: ffff914589838dc0 R08: 0000000000000000 R09: 0000000000000086
[105954.384920] R10: 000000000000000f R11: ffffa31240904be5 R12: ffff914605f868e0
[105954.384921] R13: ffff914605f86910 R14: 0000000000008010 R15: 00000000ddb7c000
[105954.384923] FS: 0000000000000000(0000) GS:ffff9163fec40000(0000) knlGS:0000000000000000
[105954.384925] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[105954.384926] CR2: 000055d31ce1d6a0 CR3: 0000000119f5e001 CR4: 0000000000770ee0
[105954.384928] PKRU: 55555554
[105954.384929] Call T
Wiz
CVE-2025-71162 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71162 [HIGH] CVE-2025-71162 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71162 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: tegra-adma: Fix use-after-free
A use-after-free bug exists in the Tegra ADMA driver when audio streams
are terminated, particularly during XRUN conditions. The issue occurs
when the DMA buffer is freed by tegra_adma_terminate_all() before the
vchan completion tasklet finishes accessing it.
The race condition follows this sequence:
DMA transfer completes, triggering an interrupt that schedules the
completion tasklet (tasklet has not executed yet)
Audio playback stops, calling tegra_adma_terminate_all() which frees the DMA buffer memory via kfree()
The scheduled tasklet finally executes, calling vchan_complete() which attempts to access
Wiz
CVE-2025-71197 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71197 CVE-2025-71197 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71197 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
w1: therm: Fix off-by-one buffer overflow in alarms_store
The sysfs buffer passed to alarms_store() is allocated with 'size + 1'
bytes and a NUL terminator is appended. However, the 'size' argument
does not account for this extra byte. The original code then allocated
'size' bytes and used strcpy() to copy 'buf', which always writes one
byte past the allocated buffer since strcpy() copies until the NUL
terminator at index 'size'.
Fix this by parsing the 'buf' parameter directly using simple_strtoll()
without allocating any intermediate memory or string copying. This
removes the overflow while simplifying the code.
Source : NVD
Published February
Wiz
CVE-2023-54203 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54203 CVE-2023-54203 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54203 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix slab-out-of-bounds in init_smb2_rsp_hdr
When smb1 mount fails, KASAN detect slab-out-of-bounds in
init_smb2_rsp_hdr like the following one.
For smb1 negotiate(56bytes) , init_smb2_rsp_hdr() for smb2 is called.
The issue occurs while handling smb1 negotiate as smb2 server operations.
Add smb server operations for smb1 (get_cmd_val, init_rsp_hdr,
allocate_rsp_buf, check_user_session) to handle smb1 negotiate so that
smb2 server operation does not handle it.
[ 411.400423] CIFS: VFS: Use of the less secure dialect vers=1.0 is
not recommended unless required for access to very old servers
[ 411.400452] CIFS: Attempting to mount \192.168.45.13
Wiz
CVE-2022-50770 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50770 CVE-2022-50770 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50770 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ocfs2: fix memory leak in ocfs2_mount_volume()
There is a memory leak reported by kmemleak:
unreferenced object 0xffff88810cc65e60 (size 32):
comm "mount.ocfs2", pid 23753, jiffies 4302528942 (age 34735.105s)
hex dump (first 32 bytes):
10 00 00 00 00 00 00 00 00 01 01 01 01 01 01 01 ................
01 01 01 01 01 01 01 01 00 00 00 00 00 00 00 00 ................
backtrace:
[ ] __kmalloc+0x4d/0x150
[ ] ocfs2_compute_replay_slots+0x121/0x330 [ocfs2]
[ ] ocfs2_check_volume+0x485/0x900 [ocfs2]
[ ] ocfs2_mount_volume.isra.0+0x1e9/0x650 [ocfs2]
[ ] ocfs2_fill_super+0xe0b/0x1740 [ocfs2]
[ ] mount_bdev+0x312/0x400
[ ] legacy_get_tree+0xed/0x1d0
[ ] vfs_ge
Wiz
CVE-2026-23156 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23156 [HIGH] CVE-2026-23156 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23156 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
efivarfs: fix error propagation in efivar_entry_get()
efivar_entry_get() always returns success even if the underlying
__efivar_entry_get() fails, masking errors.
This may result in uninitialized heap memory being copied to userspace
in the efivarfs_file_read() path.
Fix it by returning the error from __efivar_entry_get().
Source : NVD
## 7.8
Score
Published February 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.3
Exploitation Probability (EPSS) N/A
Affect
Wiz
CVE-2025-68290 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68290 CVE-2025-68290 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68290 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
most: usb: fix double free on late probe failure
The MOST subsystem has a non-standard registration function which frees
the interface on registration failures and on deregistration.
This unsurprisingly leads to bugs in the MOST drivers, and a couple of
recent changes turned a reference underflow and use-after-free in the
USB driver into several double free and a use-after-free on late probe
failures.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitatio
Wiz
CVE-2025-68737 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68737 CVE-2025-68737 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68737 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64/pageattr: Propagate return value from __change_memory_common
The rodata=on security measure requires that any code path which does
vmalloc -> set_memory_ro/set_memory_rox must protect the linear map alias
too. Therefore, if such a call fails, we must abort set_memory_* and caller
must take appropriate action; currently we are suppressing the error, and
there is a real chance of such an error arising post commit a166563e7ec3
("arm64: mm: support large block mapping when rodata=full"). Therefore,
propagate any error to the caller.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Pu
Wiz
CVE-2023-54176 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54176 CVE-2023-54176 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54176 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: stricter state check in mptcp_worker
As reported by Christoph, the mptcp protocol can run the
worker when the relevant msk socket is in an unexpected state:
connect()
// incoming reset + fastclose
// the mptcp worker is scheduled
mptcp_disconnect()
// msk is now CLOSED
listen()
mptcp_worker()
Leading to the following splat:
divide error: 0000 [#1] PREEMPT SMP
CPU: 1 PID: 21 Comm: kworker/1:0 Not tainted 6.3.0-rc1-gde5e8fd0123c #11
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014
Workqueue: events mptcp_worker
RIP: 0010:__tcp_select_window+0x22c/0x4b0 net/ipv4/tcp_output.c:3018
RSP: 0018:ffffc900000b3c98 E
Wiz
CVE-2023-54092 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54092 CVE-2023-54092 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54092 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: s390: pv: fix index value of replaced ASCE
The index field of the struct page corresponding to a guest ASCE should
be 0. When replacing the ASCE in s390_replace_asce(), the index of the
new ASCE should also be set to 0.
Having the wrong index might lead to the wrong addresses being passed
around when notifying pte invalidations, and eventually to validity
intercepts (VM crash) if the prefix gets unmapped and the notifier gets
called with the wrong address.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2026-23256 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23256 CVE-2026-23256 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23256 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: liquidio: Fix off-by-one error in VF setup_nic_devices() cleanup
In setup_nic_devices(), the initialization loop jumps to the label
setup_nic_dev_free on failure. The current cleanup loop while(i--)
skip the failing index i, causing a memory leak.
Fix this by changing the loop to iterate from the current index i
down to 0.
Compile tested only. Issue found using code review.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probabi
Wiz
CVE-2025-68362 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68362 CVE-2025-68362 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68362 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtl818x: rtl8187: Fix potential buffer underflow in rtl8187_rx_cb()
The rtl8187_rx_cb() calculates the rx descriptor header address
by subtracting its size from the skb tail pointer.
However, it does not validate if the received packet
(skb->len from urb->actual_length) is large enough to contain this
header.
If a truncated packet is received, this will lead to a buffer
underflow, reading memory before the start of the skb data area,
and causing a kernel panic.
Add length checks for both rtl8187 and rtl8187b descriptor headers
before attempting to access them, dropping the packet cleanly if the
check fails.
Source : NVD
## 5.5
Score
Pu
Wiz
CVE-2025-68360 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68360 CVE-2025-68360 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68360 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: wed: use proper wed reference in mt76 wed driver callabacks
MT7996 driver can use both wed and wed_hif2 devices to offload traffic
from/to the wireless NIC. In the current codebase we assume to always
use the primary wed device in wed callbacks resulting in the following
crash if the hw runs wed_hif2 (e.g. 6GHz link).
[ 297.455876] Unable to handle kernel read from unreadable memory at virtual address 000000000000080a
[ 297.464928] Mem abort info:
[ 297.467722] ESR = 0x0000000096000005
[ 297.471461] EC = 0x25: DABT (current EL), IL = 32 bits
[ 297.476766] SET = 0, FnV = 0
[ 297.479809] EA = 0, S1PTW = 0
[ 297.482940] FSC = 0x05: level 1
Wiz
CVE-2023-53860 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53860 CVE-2023-53860 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53860 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm: don't attempt to queue IO under RCU protection
dm looks up the table for IO based on the request type, with an
assumption that if the request is marked REQ_NOWAIT, it's fine to
attempt to submit that IO while under RCU read lock protection. This
is not OK, as REQ_NOWAIT just means that we should not be sleeping
waiting on other IO, it does not mean that we can't potentially
schedule.
A simple test case demonstrates this quite nicely:
int main(int argc, char *argv[])
{
struct iovec iov;
int fd;
fd = open("/dev/dm-0", O_RDONLY | O_DIRECT);
posix_memalign(&iov.iov_base, 4096, 4096);
iov.iov_len = 4096;
preadv2(fd, &iov, 1, 0, RWF_NOWAIT);
return
Wiz
CVE-2026-23022 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23022 [MEDIUM] CVE-2026-23022 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23022 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix memory leak in idpf_vc_core_deinit()
Make sure to free hw->lan_regs. Reported by kmemleak during reset:
unreferenced object 0xff1b913d02a936c0 (size 96):
comm "kworker/u258:14", pid 2174, jiffies 4294958305
hex dump (first 32 bytes):
00 00 00 c0 a8 ba 2d ff 00 00 00 00 00 00 00 00 ......-.........
00 00 40 08 00 00 00 00 00 00 25 b3 a8 ba 2d ff ..@.......%...-.
backtrace (crc 36063c4f):
__kmalloc_noprof+0x48f/0x890
idpf_vc_core_init+0x6ce/0x9b0 [idpf]
idpf_vc_event_task+0x1fb/0x350 [idpf]
process_one_work+0x226/0x6d0
worker_thread+0x19e/0x340
kthread+0x10f/0x250
ret_from_fork+0x251/0x2b0
ret_from_fork_asm+0x1a/0x30
Source : NVD
## 5.5
Wiz
CVE-2026-23349 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23349 CVE-2026-23349 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23349 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: pidff: Fix condition effect bit clearing
As reported by MPDarkGuy on discord, NULL pointer dereferences were
happening because not all the conditional effects bits were cleared.
Properly clear all conditional effect bits from ffbit
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-headers
kernel-kdump
Sources
NVD
Debian 14 Has Fix Added at: Mar 26, 2026
Red Hat 6
Wiz
CVE-2025-71152 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71152 [HIGH] CVE-2025-71152 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71152 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: dsa: properly keep track of conduit reference
## Problem description
DSA has a mumbo-jumbo of reference handling of the conduit net device
and its kobject which, sadly, is just wrong and doesn't make sense.
There are two distinct problems.
The OF path, which uses of_find_net_device_by_node(), never releases
the elevated refcount on the conduit's kobject. Nominally, the OF and
non-OF paths should result in objects having identical reference
counts taken, and it is already suspicious that
dsa_dev_to_net_device() has a put_device() call which is missing in
dsa_port_parse_of(), but we can actually even verify that an issue
exists. With CONFIG_
Wiz
CVE-2025-68210 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68210 CVE-2025-68210 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68210 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: avoid infinite loop due to incomplete zstd-compressed data
Currently, the decompression logic incorrectly spins if compressed
data is truncated in crafted (deliberately corrupted) images.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
cluster-md-kmp-azure
dtb-nvidia
Sources
NVD
Debian 13, 14 Has Fix Added at: Dec 17, 2025
Ubuntu 24.04, 25.10 Severity MEDIUM Has Fi
Wiz
CVE-2025-68349 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68349 CVE-2025-68349 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68349 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSv4/pNFS: Clear NFS_INO_LAYOUTCOMMIT in pnfs_mark_layout_stateid_invalid
Fixes a crash when layout is null during this call stack:
write_inode
-> nfs4_write_inode
-> pnfs_layoutcommit_inode
pnfs_set_layoutcommit relies on the lseg refcount to keep the layout
around. Need to clear NFS_INO_LAYOUTCOMMIT otherwise we might attempt
to reference a null layout.
Source : NVD
## 4.7
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Rocky Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploi
Wiz
CVE-2023-54278 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54278 CVE-2023-54278 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54278 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/vmem: split pages when debug pagealloc is enabled
Since commit bb1520d581a3 ("s390/mm: start kernel with DAT enabled")
the kernel crashes early during boot when debug pagealloc is enabled:
mem auto-init: stack:off, heap alloc:off, heap free:off
addressing exception: 0005 ilc:2 [#1] SMP DEBUG_PAGEALLOC
Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 6.5.0-rc3-09759-gc5666c912155 #630
[..]
Krnl Code: 00000000001325f6: ec5600248064 cgrj %r5,%r6,8,000000000013263e
00000000001325fc: eb880002000c srlg %r8,%r8,2
#0000000000132602: b2210051 ipte %r5,%r1,%r0,0
>0000000000132606: b90400d1 lgr %r13,%r1
000000000013260a: 41605008 la %r6,8(%r5)
Wiz
CVE-2023-54293 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54293 CVE-2023-54293 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54293 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bcache: fixup btree_cache_wait list damage
We get a kernel crash about "list_add corruption. next->prev should be
prev (ffff9c801bc01210), but was ffff9c77b688237c.
(next=ffffae586d8afe68)."
crash> struct list_head 0xffff9c801bc01210
struct list_head {
next = 0xffffae586d8afe68,
prev = 0xffffae586d8afe68
}
crash> struct list_head 0xffff9c77b688237c
struct list_head {
next = 0x0,
prev = 0x0
}
crash> struct list_head 0xffffae586d8afe68
struct list_head struct: invalid kernel virtual address: ffffae586d8afe68 type: "gdb_readmem_callback"
Cannot access memory at address 0xffffae586d8afe68
[230469.019492] Call Trace:
[230469.032041] prepare_to_wait+0x8
Wiz
CVE-2026-23056 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23056 CVE-2026-23056 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23056 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
uacce: implement mremap in uacce_vm_ops to return -EPERM
The current uacce_vm_ops does not support the mremap operation of
vm_operations_struct. Implement .mremap to return -EPERM to remind
users.
The reason we need to explicitly disable mremap is that when the
driver does not implement .mremap, it uses the default mremap
method. This could lead to a risk scenario:
An application might first mmap address p1, then mremap to p2,
followed by munmap(p1), and finally munmap(p2). Since the default
mremap copies the original vma's vm_private_data (i.e., q) to the
new vma, both munmap operations would trigger vma_close, causing
q->qfr to be freed twice(qf
Wiz
CVE-2023-53863 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53863 CVE-2023-53863 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53863 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netlink: do not hard code device address lenth in fdb dumps
syzbot reports that some netdev devices do not have a six bytes
address [1]
Replace ETH_ALEN by dev->addr_len.
[1] (Case of a device where dev->addr_len = 4)
BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline]
BUG: KMSAN: kernel-infoleak in copyout+0xb8/0x100 lib/iov_iter.c:169
instrument_copy_to_user include/linux/instrumented.h:114 [inline]
copyout+0xb8/0x100 lib/iov_iter.c:169
_copy_to_iter+0x6d8/0x1d00 lib/iov_iter.c:536
copy_to_iter include/linux/uio.h:206 [inline]
simple_copy_to_iter+0x68/0xa0 net/core/datagram.c:513
__skb_datagram_iter+
Wiz
CVE-2026-23297 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23297 CVE-2026-23297 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23297 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit().
syzbot reported memory leak of struct cred. [0]
nfsd_nl_threads_set_doit() passes get_current_cred() to
nfsd_svc(), but put_cred() is not called after that.
The cred is finally passed down to _svc_xprt_create(),
which calls get_cred() with the cred for struct svc_xprt.
The ownership of the refcount by get_current_cred() is not
transferred to anywhere and is just leaked.
nfsd_svc() is also called from write_threads(), but it does
not bump file->f_cred there.
nfsd_nl_threads_set_doit() is called from sendmsg() and
current->cred does not go away.
Let's use current_cred() in nfsd_nl_threads_se
Wiz
CVE-2025-68193 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68193 CVE-2025-68193 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68193 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/guc: Add devm release action to safely tear down CT
When a buffer object (BO) is allocated with the XE_BO_FLAG_GGTT_INVALIDATE
flag, the driver initiates TLB invalidation requests via the CTB mechanism
while releasing the BO. However a premature release of the CTB BO can lead
to system crashes, as observed in:
Oops: Oops: 0000 [#1] SMP NOPTI
RIP: 0010:h2g_write+0x2f3/0x7c0 [xe]
Call Trace:
guc_ct_send_locked+0x8b/0x670 [xe]
xe_guc_ct_send_locked+0x19/0x60 [xe]
send_tlb_invalidation+0xb4/0x460 [xe]
xe_gt_tlb_invalidation_ggtt+0x15e/0x2e0 [xe]
ggtt_invalidate_gt_tlb.part.0+0x16/0x90 [xe]
ggtt_node_remove+0x110/0x140 [xe]
xe_ggtt_node_remove+0x
Wiz
CVE-2023-54120 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54120 CVE-2023-54120 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54120 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: Fix race condition in hidp_session_thread
There is a potential race condition in hidp_session_thread that may
lead to use-after-free. For instance, the timer is active while
hidp_del_timer is called in hidp_session_thread(). After hidp_session_put,
then 'session' will be freed, causing kernel panic when hidp_idle_timeout
is running.
The solution is to use del_timer_sync instead of del_timer.
Here is the call trace:
? hidp_session_probe+0x780/0x780
call_timer_fn+0x2d/0x1e0
__run_timers.part.0+0x569/0x940
hidp_session_probe+0x780/0x780
call_timer_fn+0x1e0/0x1e0
ktime_get+0x5c/0xf0
lapic_next_deadline+0x2c/0x40
clockevents_program_event+0
Wiz
CVE-2025-40337 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40337 CVE-2025-40337 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40337 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: stmmac: Correctly handle Rx checksum offload errors
The stmmac_rx function would previously set skb->ip_summed to
CHECKSUM_UNNECESSARY if hardware checksum offload (CoE) was enabled
and the packet was of a known IP ethertype.
However, this logic failed to check if the hardware had actually
reported a checksum error. The hardware status, indicating a header or
payload checksum failure, was being ignored at this stage. This could
cause corrupt packets to be passed up the network stack as valid.
csum_none
Source : NVD
## 5.1
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Wiz
CVE-2022-50872 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50872 CVE-2022-50872 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50872 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ARM: OMAP2+: Fix memory leak in realtime_counter_init()
The "sys_clk" resource is malloced by clk_get(),
it is not released when the function return.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-lowlatency
kernel-kdump-devel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 7, 8 Severity LOW No Fix Adde
Wiz
CVE-2022-50783 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50783 CVE-2022-50783 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50783 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: use proper req destructor for IPv6
Before, only the destructor from TCP request sock in IPv4 was called
even if the subflow was IPv6.
It is important to use the right destructor to avoid memory leaks with
some advanced IPv6 features, e.g. when the request socks contain
specific IPv6 options.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-modules-internal
Wiz
CVE-2025-71113 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71113 [MEDIUM] CVE-2025-71113 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71113 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: af_alg - zero initialize memory allocated via sock_kmalloc
Several crypto user API contexts and requests allocated with
sock_kmalloc() were left uninitialized, relying on callers to
set fields explicitly. This resulted in the use of uninitialized
data in certain error paths or when new fields are added in the
future.
The ACVP patches also contain two user-space interface files:
algif_kpp.c and algif_akcipher.c. These too rely on proper
initialization of their context structures.
A particular issue has been observed with the newly added
'inflight' variable introduced in af_alg_ctx by commit:
67b164a871af ("crypto: af_alg - Disallow multipl
Wiz
CVE-2026-23078 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23078 [HIGH] CVE-2026-23078 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23078 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: scarlett2: Fix buffer overflow in config retrieval
The scarlett2_usb_get_config() function has a logic error in the
endianness conversion code that can cause buffer overflows when
count > 1.
if (size == 2)
size
count
count * 2
size
Fix by checking the element size (config_item->size) instead of the
total buffer size. This ensures the endianness conversion matches the
actual element type.
Source : NVD
## 7.8
Score
Published February 4, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Pro
Wiz
CVE-2026-23276 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23276 CVE-2026-23276 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23276 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: add xmit recursion limit to tunnel xmit functions
Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own
recursion limit. When a bond device in broadcast mode has GRE tap
interfaces as slaves, and those GRE tunnels route back through the
bond, multicast/broadcast traffic triggers infinite recursion between
bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing
kernel stack overflow.
The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not
sufficient because tunnel recursion involves route lookups and full IP
output, consuming much more stack per level. Use a lower limit of 4
(IP_TUNNEL_RECURSION_LIMIT) to pre
Wiz
CVE-2023-54326 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54326 CVE-2023-54326 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54326 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
misc: pci_endpoint_test: Free IRQs before removing the device
In pci_endpoint_test_remove(), freeing the IRQs after removing the device
creates a small race window for IRQs to be received with the test device
memory already released, causing the IRQ handler to access invalid memory,
resulting in an oops.
Free the device IRQs before removing the device to avoid this issue.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability
Wiz
CVE-2023-54095 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54095 CVE-2023-54095 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54095 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/iommu: Fix notifiers being shared by PCI and VIO buses
fail_iommu_setup() registers the fail_iommu_bus_notifier struct to both
PCI and VIO buses. struct notifier_block is a linked list node, so this
causes any notifiers later registered to either bus type to also be
registered to the other since they share the same node.
This causes issues in (at least) the vgaarb code, which registers a
notifier for PCI buses. pci_notify() ends up being called on a vio
device, converted with to_pci_dev() even though it's not a PCI device,
and finally makes a bad access in vga_arbiter_add_pci_device() as
discovered with KASAN:
BUG: KASAN: slab-out-of-bound
Wiz
CVE-2022-50703 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50703 CVE-2022-50703 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50703 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
soc: qcom: smsm: Fix refcount leak bugs in qcom_smsm_probe()
There are two refcount leak bugs in qcom_smsm_probe():
(1) The 'local_node' is escaped out from for_each_child_of_node() as
the break of iteration, we should call of_node_put() for it in error
path or when it is not used anymore.
(2) The 'node' is escaped out from for_each_available_child_of_node()
as the 'goto', we should call of_node_put() for it in goto target.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabi
Wiz
CVE-2025-68758 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68758 CVE-2025-68758 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68758 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
backlight: led-bl: Add devlink to supplier LEDs
LED Backlight is a consumer of one or multiple LED class devices, but
devlink is currently unable to create correct supplier-producer links when
the supplier is a class device. It creates instead a link where the
supplier is the parent of the expected device.
One consequence is that removal order is not correctly enforced.
Issues happen for example with the following sections in a device tree
overlay:
// An LED driver chip
pca9632@62 {
compatible = "nxp,pca9632";
reg = ;
// ...
addon_led_pwm: led-pwm@3 {
reg = ;
label = "addon:led:pwm";
};
};
backlight-addon {
compatible = "led-backlight";
leds =
Wiz
CVE-2025-68819 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68819 CVE-2025-68819 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68819 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: dvb-usb: dtv5100: fix out-of-bounds in dtv5100_i2c_msg()
rlen value is a user-controlled value, but dtv5100_i2c_msg() does not
check the size of the rlen value. Therefore, if it is set to a value
larger than sizeof(st->data), an out-of-bounds vuln occurs for st->data.
Therefore, we need to add proper range checking to prevent this vuln.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages
Wiz
CVE-2025-71154 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71154 [MEDIUM] CVE-2025-71154 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71154 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: rtl8150: fix memory leak on usb_submit_urb() failure
In async_set_registers(), when usb_submit_urb() fails, the allocated
async_req structure and URB are not freed, causing a memory leak.
The completion callback async_set_reg_cb() is responsible for freeing
these allocations, but it is only called after the URB is successfully
submitted and completes (successfully or with error). If submission
fails, the callback never runs and the memory is leaked.
Fix this by freeing both the URB and the request structure in the error
path when usb_submit_urb() fails.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Scor
Wiz
CVE-2023-54173 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54173 CVE-2023-54173 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54173 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Disable preemption in bpf_event_output
We received report [1] of kernel crash, which is caused by
using nesting protection without disabled preemption.
The bpf_event_output can be called by programs executed by
bpf_prog_run_array_cg function that disabled migration but
keeps preemption enabled.
This can cause task to be preempted by another one inside the
nesting protection and lead eventually to two tasks using same
perf_sample_data buffer and cause crashes like:
BUG: kernel NULL pointer dereference, address: 0000000000000001
#PF: supervisor instruction fetch in kernel mode
#PF: error_code(0x0010) - not-present page
...
? perf_output_sample
Wiz
CVE-2017-20229 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 9.3
CVE-2017-20229 [CRITICAL] CVE-2017-20229 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2017-20229 :
Linux Ubuntu vulnerability analysis and mitigation
MAWK 1.3.3-17 and prior contains a stack-based buffer overflow vulnerability that allows attackers to execute arbitrary code by exploiting inadequate boundary checks on user-supplied input. Attackers can craft malicious input that overflows the stack buffer and execute a return-oriented programming chain to spawn a shell with application privileges.
Source : NVD
## 9.3
Score
Published March 28, 2026
Severity CRITICAL
CNA Score 9.3
Affected Technologies
Linux Ubuntu
Echo
Has Public Exploit Yes
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 21.4
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
mawk
Sources
NVD
Ec
Wiz
CVE-2025-71084 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71084 [MEDIUM] CVE-2025-71084 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71084 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/cm: Fix leaking the multicast GID table reference
If the CM ID is destroyed while the CM event for multicast creating is
still queued the cancel_work_sync() will prevent the work from running
which also prevents destroying the ah_attr. This leaks a refcount and
triggers a WARN:
GID entry ref leak for dev syz1 index 2 ref=573
WARNING: CPU: 1 PID: 655 at drivers/infiniband/core/cache.c:809 release_gid_table drivers/infiniband/core/cache.c:806 [inline]
WARNING: CPU: 1 PID: 655 at drivers/infiniband/core/cache.c:809 gid_table_release_one+0x284/0x3cc drivers/infiniband/core/cache.c:886
Destroy the ah_attr after canceling the work, it is safe to ca
Wiz
CVE-2025-68292 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68292 CVE-2025-68292 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68292 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/memfd: fix information leak in hugetlb folios
When allocating hugetlb folios for memfd, three initialization steps are
missing:
Folios are not zeroed, leading to kernel memory disclosure to userspace
Folios are not marked uptodate before adding to page cache
hugetlb_fault_mutex is not taken before hugetlb_add_to_page_cache()
The memfd allocation path bypasses the normal page fault handler
(hugetlb_no_page) which would handle all of these initialization steps.
This is problematic especially for udmabuf use cases where folios are
pinned and directly accessed by userspace via DMA.
Fix by matching the initialization pattern used in hugetlb_no_pa
Wiz
CVE-2023-54128 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54128 CVE-2023-54128 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54128 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: drop peer group ids under namespace lock
When cleaning up peer group ids in the failure path we need to make sure
to hold on to the namespace lock. Otherwise another thread might just
turn the mount from a shared into a non-shared mount concurrently.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-livepatch-5.15.108-65.141
kernel-obs-build
Sources
NVD
Debian 12,
Wiz
CVE-2025-68339 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68339 CVE-2025-68339 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68339 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
atm/fore200e: Fix possible data race in fore200e_open()
Protect access to fore200e->available_cell_rate with rate_mtx lock in the
error handling path of fore200e_open() to prevent a data race.
The field fore200e->available_cell_rate is a shared resource used to track
available bandwidth. It is concurrently accessed by fore200e_open(),
fore200e_close(), and fore200e_change_qos().
In fore200e_open(), the lock rate_mtx is correctly held when subtracting
vcc->qos.txtp.max_pcr from available_cell_rate to reserve bandwidth.
However, if the subsequent call to fore200e_activate_vcin() fails, the
function restores the reserved bandwidth by adding back to
a
Wiz
CVE-2023-54012 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54012 CVE-2023-54012 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54012 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: fix stack overflow when LRO is disabled for virtual interfaces
When the virtual interface's feature is updated, it synchronizes the
updated feature for its own lower interface.
This propagation logic should be worked as the iteration, not recursively.
But it works recursively due to the netdev notification unexpectedly.
This problem occurs when it disables LRO only for the team and bonding
interface type.
team0
|
+------+------+-----+-----+
| | | | |
team1 team2 team3 ... team200
If team0's LRO feature is updated, it generates the NETDEV_FEAT_CHANGE
event to its own lower interfaces(team1 ~ team200).
It is worked by netdev_sync_lower_feature
Wiz
CVE-2026-23421 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23421 CVE-2026-23421 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23421 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/configfs: Free ctx_restore_mid_bb in release
ctx_restore_mid_bb memory is allocated in wa_bb_store(), but
xe_config_device_release() only frees ctx_restore_post_bb.
Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation
when the configfs device is removed.
(cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f)
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4
Exploitation Probability (EPSS) N/A
Affected packages an
Wiz
CVE-2023-54220 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54220 CVE-2023-54220 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54220 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
serial: 8250: Fix oops for port->pm on uart_change_pm()
Unloading a hardware specific 8250 driver can produce error "Unable to
handle kernel paging request at virtual address" about ten seconds after
unloading the driver. This happens on uart_hangup() calling
uart_change_pm().
Turns out commit 04e82793f068 ("serial: 8250: Reinit port->pm on port
specific driver unbind") was only a partial fix. If the hardware specific
driver has initialized port->pm function, we need to clear port->pm too.
Just reinitializing port->ops does not do this. Otherwise serial8250_pm()
will call port->pm() instead of serial8250_do_pm().
Source : NVD
Published December 3
Wiz
CVE-2023-53849 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53849 CVE-2023-53849 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53849 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm: fix workqueue leak on bind errors
Make sure to destroy the workqueue also in case of early errors during
bind (e.g. a subcomponent failing to bind).
Since commit c3b790ea07a1 ("drm: Manage drm_mode_config_init with
drmm_") the mode config will be freed when the drm device is released
also when using the legacy interface, but add an explicit cleanup for
consistency and to facilitate backporting.
Patchwork: https://patchwork.freedesktop.org/patch/525093/
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2025-68361 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68361 CVE-2025-68361 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68361 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: limit the level of fs stacking for file-backed mounts
Otherwise, it could cause potential kernel stack overflow (e.g., EROFS
mounting itself).
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure
linux-azure-6.17
Sources
NVD
Debian 13, 14 Has Fix Added at: Dec 26, 2025
Red Hat 10 Severity MEDIUM No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Sever
Wiz
CVE-2023-54142 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54142 CVE-2023-54142 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54142 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gtp: Fix use-after-free in __gtp_encap_destroy().
syzkaller reported use-after-free in __gtp_encap_destroy(). 0
It shows the same process freed sk and touched it illegally.
Commit e198987e7dd7 ("gtp: fix suspicious RCU usage") added lock_sock()
and release_sock() in __gtp_encap_destroy() to protect sk->sk_user_data,
but release_sock() is called after sock_put() releases the last refcnt.
CPU: 1 PID: 2401 Comm: syz-executor.2 Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Call Trace: __dump_stack lib/dump_stack.c:88 [inline]
dump_stack_
Wiz
CVE-2026-23369 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23369 CVE-2026-23369 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23369 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i2c: i801: Revert "i2c: i801: replace acpi_lock with I2C bus lock"
This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1.
Under rare circumstances, multiple udev threads can collect i801 device
info on boot and walk i801_acpi_io_handler somewhat concurrently. The
first will note the area is reserved by acpi to prevent further touches.
This ultimately causes the area to be deregistered. The second will
enter i801_acpi_io_handler after the area is unregistered but before a
check can be made that the area is unregistered. i2c_lock_bus relies on
the now unregistered area containing lock_ops to lock the bus. The end
result is a kernel panic on bo
Wiz
CVE-2022-50843 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50843 CVE-2022-50843 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50843 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm clone: Fix UAF in clone_dtr()
Dm_clone also has the same UAF problem when dm_resume()
and dm_destroy() are concurrent.
Therefore, cancelling timer again in clone_dtr().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
kernel-default-devel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Seve
Wiz
CVE-2026-23189 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23189 [MEDIUM] CVE-2026-23189 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23189 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ceph: fix NULL pointer dereference in ceph_mds_auth_match()
The CephFS kernel client has regression starting from 6.18-rc1.
We have issue in ceph_mds_auth_match() if fs_name == NULL:
const char fs_name = mdsc->fsc->mount_options->mds_namespace;
...
if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) {
/ fsname mismatch, try next one */
return 0;
}
fs_name
-o mds_namespace=foo
This patch reworks ceph_mdsmap_decode() and namespace_equals() with
the goal of supporting the suggested concept. Now struct ceph_mdsmap
contains m_fs_name field that receives copy of extracted FS name
by ceph_extract_encoded_string(). For the case of "old" Cep
Wiz
CVE-2026-23075 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23075 [MEDIUM] CVE-2026-23075 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23075 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: esd_usb: esd_usb_read_bulk_callback(): fix URB memory leak
Fix similar memory leak as in commit 7352e1d5932a ("can: gs_usb:
gs_usb_receive_bulk_callback(): fix URB memory leak").
In esd_usb_open(), the URBs for USB-in transfers are allocated, added to
the dev->rx_submitted anchor and submitted. In the complete callback
esd_usb_read_bulk_callback(), the URBs are processed and resubmitted. In
esd_usb_close() the URBs are freed by calling
usb_kill_anchored_urbs(&dev->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the complete function is called. This means that once an
in-URB has been comp
Wiz
CVE-2023-54022 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54022 CVE-2023-54022 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54022 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: usb-audio: Fix potential memory leaks at error path for UMP open
The allocation and initialization errors at alloc_midi_urbs() that is
called at MIDI 2.0 / UMP device are supposed to be handled at the
caller side by invoking free_midi_urbs(). However, free_midi_urbs()
loops only for ep->num_urbs entries, and since ep->num_entries wasn't
updated yet at the allocation / init error in alloc_midi_urbs(), this
entry won't be released.
The intention of free_midi_urbs() is to release the whole elements, so
change the loop size to NUM_URBS to scan over all elements for fixing
the missed releases.
Also, the call of free_midi_urbs() is missing at
snd_
Wiz
CVE-2026-23002 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23002 [MEDIUM] CVE-2026-23002 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23002 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
lib/buildid: use __kernel_read() for sleepable context
Prevent a "BUG: unable to handle kernel NULL pointer dereference in
filemap_read_folio".
For the sleepable context, convert freader to use __kernel_read() instead
of direct page cache access via read_cache_folio(). This simplifies the
faultable code path by using the standard kernel file reading interface
which handles all the complexity of reading file data.
At the moment we are not changing the code for non-sleepable context which
uses filemap_get_folio() and only succeeds if the target folios are
already in memory and up-to-date. The reason is to keep the patch simple
and easier to backport
Wiz
CVE-2023-54077 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54077 CVE-2023-54077 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54077 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix memory leak if ntfs_read_mft failed
Label ATTR_ROOT in ntfs_read_mft() sets is_root = true and
ni->ni_flags |= NI_FLAG_DIR, then next attr will goto label ATTR_ALLOC
and alloc ni->dir.alloc_run. However two states are not always
consistent and can make memory leak.
attr_name in ATTR_ROOT does not fit the condition it will setis_root = true but NI_FLAG_DIR is not set.
next attr_name in ATTR_ALLOC fits the condition and allocni->dir.alloc_run
in cleanup function ni_clear(), when NI_FLAG_DIR is set, it freesni->dir.alloc_run, otherwise it frees ni->file.run
because NI_FLAG_DIR is not set in this case, ni->dir.alloc_run isleaked as kme
Wiz
CVE-2026-23109 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23109 [MEDIUM] CVE-2026-23109 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23109 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/writeback: skip AS_NO_DATA_INTEGRITY mappings in wait_sb_inodes()
Above the while() loop in wait_sb_inodes(), we document that we must wait
for all pages under writeback for data integrity. Consequently, if a
mapping, like fuse, traditionally does not have data integrity semantics,
there is no need to wait at all; we can simply skip these inodes.
This restores fuse back to prior behavior where syncs are no-ops. This
fixes a user regression where if a system is running a faulty fuse server
that does not reply to issued write requests, this causes wait_sb_inodes()
to wait forever.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severit
Wiz
CVE-2026-31403 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31403 CVE-2026-31403 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31403 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd
The /proc/fs/nfs/exports proc entry is created at module init
and persists for the module's lifetime. exports_proc_open()
captures the caller's current network namespace and stores
its svc_export_cache in seq->private, but takes no reference
on the namespace. If the namespace is subsequently torn down
(e.g. container destruction after the opener does setns() to a
different namespace), nfsd_net_exit() calls nfsd_export_shutdown()
which frees the cache. Subsequent reads on the still-open fd
dereference the freed cache_detail, walking a freed hash table.
Hold a reference on the struc
Wiz
CVE-2026-23452 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23452 CVE-2026-23452 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23452 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PM: runtime: Fix a race condition related to device removal
The following code in pm_runtime_work() may dereference the dev->parent
pointer after the parent device has been freed:
/* Maybe the parent is now able to suspend. */
if (parent && !parent->power.ignore_children) {
spin_unlock(&dev->power.lock);
spin_lock(&parent->power.lock);
rpm_idle(parent, RPM_ASYNC);
spin_unlock(&parent->power.lock);
spin_lock(&dev->power.lock);
}
Fix this by inserting a flush_work() call in pm_runtime_remove().
Without this patch blktest block/001 triggers the following complaint
sporadically:
BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160
Read of si
Wiz
CVE-2026-23153 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23153 [MEDIUM] CVE-2026-23153 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23153 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
firewire: core: fix race condition against transaction list
The list of transaction is enumerated without acquiring card lock when
processing AR response event. This causes a race condition bug when
processing AT request completion event concurrently.
This commit fixes the bug by put timer start for split transaction
expiration into the scope of lock. The value of jiffies in card structure
is referred before acquiring the lock.
Source : NVD
## 4.7
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2026-23187 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23187 [HIGH] CVE-2026-23187 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23187 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pmdomain: imx8m-blk-ctrl: fix out-of-range access of bc->domains
Fix out-of-range access of bc->domains in imx8m_blk_ctrl_remove().
Source : NVD
## 7.1
Score
Published February 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 2.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-nvidia
kernel-uek-doc
Sources
NVD
CBL-Mariner 3.0 Severity HIGH Has Fix Added at: Mar 13, 2026
Debian 11 Severity HIGH Has Fix Added at: Mar 13, 2026
Debian
Wiz
CVE-2025-68201 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68201 CVE-2025-68201 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68201 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: remove two invalid BUG_ON()s
Those can be triggered trivially by userspace.
Source : NVD
## 3.7
Score
Published December 16, 2025
Severity LOW
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-exynos
dtb-xilinx
Sources
NVD
Debian 11, 12 No Fix Added at: Dec 17, 2025
Debian 13, 14 Has Fix Added at: Dec 17, 2025
Echo Has Fix Added at: Dec 17, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No
Wiz
CVE-2026-3856 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.3
CVE-2026-3856 [MEDIUM] CVE-2026-3856 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-3856 :
Linux Ubuntu vulnerability analysis and mitigation
IBM Db2 Recovery Expert for Linux, UNIX and Windows 5.5 IF 2 could allow an attacker to modify or corrupt data due to an insecure mechanism used for verifying the integrity of the data during transmission.
Source : NVD
## 9.1
Score
Published March 17, 2026
Severity CRITICAL
CNA Score 5.3
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Mar 19, 2026
## Get a CVE risk assessment
Get a prioritized view
Wiz
CVE-2026-23225 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23225 [HIGH] CVE-2026-23225 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23225 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sched/mmcid: Don't assume CID is CPU owned on mode switch
Shinichiro reported a KASAN UAF, which is actually an out of bounds access
in the MMCID management code.
CPU0 CPU1
T1 runs in userspace
T0: fork(T4) -> Switch to per CPU CID mode
fixup() set MM_CID_TRANSIT on T1/CPU1
T4 exit()
T3 exit()
T2 exit()
T1 exit() switch to per task mode
---> Out of bounds access.
As T1 has not scheduled after T0 set the TRANSIT bit, it exits with the
TRANSIT bit set. sched_mm_cid_remove_user() clears the TRANSIT bit in
the task and drops the CID, but it does not touch the per CPU storage.
That's functionally correct because a CID is only owned by the CPU when
the
Wiz
CVE-2026-22997 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22997 [MEDIUM] CVE-2026-22997 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22997 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: can: j1939: j1939_xtp_rx_rts_session_active(): deactivate session upon receiving the second rts
Since j1939_session_deactivate_activate_next() in j1939_tp_rxtimer() is
called only when the timer is enabled, we need to call
j1939_session_deactivate_activate_next() if we cancelled the timer.
Otherwise, refcount for j1939_session leaks, which will later appear as
| unregister_netdevice: waiting for vcan0 to become free. Usage count = 2.
problem.
Source : NVD
## 5.5
Score
Published January 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Rele
Wiz
CVE-2022-50817 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50817 CVE-2022-50817 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50817 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: hsr: avoid possible NULL deref in skb_clone()
syzbot got a crash [1] in skb_clone(), caused by a bug
in hsr_get_untagged_frame().
When/if create_stripped_skb_hsr() returns NULL, we must
not attempt to call skb_clone().
While we are at it, replace a WARN_ONCE() by netdev_warn_once().
[1]
general protection fault, probably for non-canonical address 0xdffffc000000000f: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000078-0x000000000000007f]
CPU: 1 PID: 754 Comm: syz-executor.0 Not tainted 6.0.0-syzkaller-02734-g0326074ff465 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022
RIP
Wiz
CVE-2025-68328 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68328 CVE-2025-68328 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68328 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
firmware: stratix10-svc: fix bug in saving controller data
Fix the incorrect usage of platform_set_drvdata and dev_set_drvdata. They
both are of the same data and overrides each other. This resulted in the
rmmod of the svc driver to fail and throw a kernel panic for kthread_stop
and fifo free.
Source : NVD
## 6.1
Score
Published December 22, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
l
Wiz
CVE-2025-68798 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68798 CVE-2025-68798 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68798 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/x86/amd: Check event before enable to avoid GPF
On AMD machines cpuc->events[idx] can become NULL in a subtle race
condition with NMI->throttle->x86_pmu_stop().
Check event for NULL in amd_pmu_enable_all() before enable to avoid a GPF.
This appears to be an AMD only issue.
Syzkaller reported a GPF in amd_pmu_enable_all.
INFO: NMI handler (perf_event_nmi_handler) took too long to run: 13.143
msecs
Oops: general protection fault, probably for non-canonical address
0xdffffc0000000034: 0000 PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x00000000000001a0-0x00000000000001a7]
CPU: 0 UID: 0 PID: 328415 Comm: repro_36674776 Not tainted 6.1
Wiz
CVE-2025-68741 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68741 CVE-2025-68741 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68741 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Fix improper freeing of purex item
In qla2xxx_process_purls_iocb(), an item is allocated via
qla27xx_copy_multiple_pkt(), which internally calls
qla24xx_alloc_purex_item().
The qla24xx_alloc_purex_item() function may return a pre-allocated item
from a per-adapter pool for small allocations, instead of dynamically
allocating memory with kzalloc().
An error handling path in qla2xxx_process_purls_iocb() incorrectly uses
kfree() to release the item. If the item was from the pre-allocated
pool, calling kfree() on it is a bug that can lead to memory corruption.
Fix this by using the correct deallocation function,
qla24xx_free_purex_item(
Wiz
CVE-2025-40360 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40360 CVE-2025-40360 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40360 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/sysfb: Do not dereference NULL pointer in plane reset
The plane state in __drm_gem_reset_shadow_plane() can be NULL. Do not
deref that pointer, but forward NULL to the other plane-reset helpers.
Clears plane->state to NULL.
v2:
fix typo in commit description (Javier)
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-rt-debug-modules-extra
kernel-uki-virt
Sources
Wiz
CVE-2025-71229 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71229 [MEDIUM] CVE-2025-71229 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71229 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtw88: Fix alignment fault in rtw_core_enable_beacon()
rtw_core_enable_beacon() reads 4 bytes from an address that is not a
multiple of 4. This results in a crash on some systems.
Do 1 byte reads/writes instead.
Unable to handle kernel paging request at virtual address ffff8000827e0522
Mem abort info:
ESR = 0x0000000096000021
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x21: alignment fault
Data abort info:
ISV = 0, ISS = 0x00000021, ISS2 = 0x00000000
CM = 0, WnR = 0, TnD = 0, TagAccess = 0
GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000005492000
[ffff8000
Wiz
CVE-2026-23237 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23237 [MEDIUM] CVE-2026-23237 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23237 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: classmate-laptop: Add missing NULL pointer checks
In a few places in the Classmate laptop driver, code using the accel
object may run before that object's address is stored in the driver
data of the input device using it.
For example, cmpc_accel_sensitivity_store_v4() is the "show" method
of cmpc_accel_sensitivity_attr_v4 which is added in cmpc_accel_add_v4(),
before calling dev_set_drvdata() for inputdev->dev. If the sysfs
attribute is accessed prematurely, the dev_get_drvdata(&inputdev->dev)
call in in cmpc_accel_sensitivity_store_v4() returns NULL which
leads to a NULL pointer dereference going forward.
Moreover, sysfs attributes
Wiz
CVE-2026-23445 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23445 CVE-2026-23445 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23445 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
igc: fix page fault in XDP TX timestamps handling
If an XDP application that requested TX timestamping is shutting down
while the link of the interface in use is still up the following kernel
splat is reported:
[ 883.803618] [ T1554] BUG: unable to handle page fault for address: ffffcfb6200fd008
...
[ 883.803650] [ T1554] Call Trace:
[ 883.803652] [ T1554] [ 883.803654] [ T1554] igc_ptp_tx_tstamp_event+0xdf/0x160 [igc]
[ 883.803660] [ T1554] igc_tsync_interrupt+0x2d5/0x300 [igc]
...
During shutdown of the TX ring the xsk_meta pointers are left behind, so
that the IRQ handler is trying to touch them.
This issue is now being fixed by cleaning up th
Wiz
CVE-2023-54036 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54036 CVE-2023-54036 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54036 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtl8xxxu: Fix memory leaks with RTL8723BU, RTL8192EU
The wifi + bluetooth combo chip RTL8723BU can leak memory (especially?)
when it's connected to a bluetooth audio device. The busy bluetooth
traffic generates lots of C2H (card to host) messages, which are not
freed correctly.
To fix this, move the dev_kfree_skb() call in rtl8xxxu_c2hcmd_callback()
inside the loop where skb_dequeue() is called.
The RTL8192EU leaks memory because the C2H messages are added to the
queue and left there forever. (This was fine in the past because it
probably wasn't sending any C2H messages until commit e542e66b7c2e
("wifi: rtl8xxxu: gen2: Turn on the rate contr
Wiz
CVE-2023-53841 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53841 CVE-2023-53841 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53841 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
devlink: report devlink_port_type_warn source device
devlink_port_type_warn is scheduled for port devlink and warning
when the port type is not set. But from this warning it is not easy
found out which device (driver) has no devlink port set.
[ 3709.975552] Type was not set for devlink port.
[ 3709.975579] WARNING: CPU: 1 PID: 13092 at net/devlink/leftover.c:6775 devlink_port_type_warn+0x11/0x20
[ 3709.993967] Modules linked in: openvswitch nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nfnetlink bluetooth rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs vhost_net vhost vhost_iotlb tap tun bridge stp llc
Wiz
CVE-2022-50702 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50702 CVE-2022-50702 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50702 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vdpa_sim: fix possible memory leak in vdpasim_net_init() and vdpasim_blk_init()
Inject fault while probing module, if device_register() fails in
vdpasim_net_init() or vdpasim_blk_init(), but the refcount of kobject is
not decreased to 0, the name allocated in dev_set_name() is leaked.
Fix this by calling put_device(), so that name can be freed in
callback function kobject_cleanup().
(vdpa_sim_net)
unreferenced object 0xffff88807eebc370 (size 16):
comm "modprobe", pid 3848, jiffies 4362982860 (age 18.153s)
hex dump (first 16 bytes):
76 64 70 61 73 69 6d 5f 6e 65 74 00 6b 6b 6b a5 vdpasim_net.kkk.
backtrace:
[ ] __kmalloc_node_track_caller+0x4e/0x150
Wiz
CVE-2026-23420 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23420 CVE-2026-23420 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23420 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: wlcore: Fix a locking bug
Make sure that wl->mutex is locked before it is unlocked. This has been
detected by the Clang thread-safety analyzer.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-fips
kernel-abi-whitelists
Sources
NVD
Debian 11, 12, 13 No Fix Added at: Apr 05, 2026
Debian 14 Has Fix Added at: Apr 05, 2026
Echo Has Fix Added at: Apr 05, 2026
Red Hat
Wiz
CVE-2022-50840 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50840 CVE-2022-50840 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50840 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: snic: Fix possible UAF in snic_tgt_create()
Smatch reports a warning as follows:
drivers/scsi/snic/snic_disc.c:307 snic_tgt_create() warn:
'&tgt->list' not removed from list
If device_add() fails in snic_tgt_create(), tgt will be freed, but
tgt->list will not be removed from snic->disc.tgt_list, then list traversal
may cause UAF.
Remove from snic->disc.tgt_list before free().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation
Wiz
CVE-2025-68816 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68816 CVE-2025-68816 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68816 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5: fw_tracer, Validate format string parameters
Add validation for format string parameters in the firmware tracer to
prevent potential security vulnerabilities and crashes from malformed
format strings received from firmware.
The firmware tracer receives format strings from the device firmware and
uses them to format trace messages. Without proper validation, bad
firmware could provide format strings with invalid format specifiers
(e.g., %s, %p, %n) that could lead to crashes, or other undefined
behavior.
Add mlx5_tracer_validate_params() to validate that all format specifiers
in trace strings are limited to safe integer/hex formats (%x, %
Wiz
CVE-2023-54002 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54002 CVE-2023-54002 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54002 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix assertion of exclop condition when starting balance
Balance as exclusive state is compatible with paused balance and device
add, which makes some things more complicated. The assertion of valid
states when starting from paused balance needs to take into account two
more states, the combinations can be hit when there are several threads
racing to start balance and device add. This won't typically happen when
the commands are started from command line.
Scenario 1: With exclusive_operation state == BTRFS_EXCLOP_NONE.
Concurrently adding multiple devices to the same mount point and
btrfs_exclop_finish executed finishes before assertion in
b
Wiz
CVE-2022-50888 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50888 CVE-2022-50888 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50888 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
remoteproc: qcom: q6v5: Fix potential null-ptr-deref in q6v5_wcss_init_mmio()
q6v5_wcss_init_mmio() will call platform_get_resource_byname() that may
fail and return NULL. devm_ioremap() will use res->start as input, which
may causes null-ptr-deref. Check the ret value of
platform_get_resource_byname() to avoid the null-ptr-deref.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
Wiz
CVE-2023-54057 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54057 CVE-2023-54057 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54057 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommu/amd: Add a length limitation for the ivrs_acpihid command-line parameter
The 'acpiid' buffer in the parse_ivrs_acpihid function may overflow,
because the string specifier in the format string sscanf()
has no width limitation.
Found by InfoTeCS on behalf of Linux Verification Center
(linuxtesting.org) with SVACE.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt
Wiz
CVE-2026-23031 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23031 CVE-2026-23031 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23031 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_receive_bulk_callback(): fix URB memory leak
In gs_can_open(), the URBs for USB-in transfers are allocated, added to the
parent->rx_submitted anchor and submitted. In the complete callback
gs_usb_receive_bulk_callback(), the URB is processed and resubmitted. In
gs_can_close() the URBs are freed by calling
usb_kill_anchored_urbs(parent->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the complete function is called. This means that once an
in-URB has been completed, it is no longer anchored and is ultimately not
released in gs_can_close().
Fix the memory leak by anchoring t
Wiz
CVE-2022-50762 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50762 CVE-2022-50762 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50762 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Avoid UBSAN error on true_sectors_per_clst()
syzbot reported UBSAN error as below:
[ 76.901829][ T6677] ================================================================================
[ 76.903908][ T6677] UBSAN: shift-out-of-bounds in fs/ntfs3/super.c:675:13
[ 76.905363][ T6677] shift exponent -247 is negative
This patch avoid this error.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected p
Wiz
CVE-2023-54288 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54288 CVE-2023-54288 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54288 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: fortify the spinlock against deadlock by interrupt
In the function ieee80211_tx_dequeue() there is a particular locking
sequence:
begin:
spin_lock(&local->queue_stop_reason_lock);
q_stopped = local->queue_stop_reasons[q];
spin_unlock(&local->queue_stop_reason_lock);
However small the chance (increased by ftracetest), an asynchronous
interrupt can occur in between of spin_lock() and spin_unlock(),
and the interrupt routine will attempt to lock the same
&local->queue_stop_reason_lock again.
This will cause a costly reset of the CPU and the wifi device or an
altogether hang in the single CPU and single core scenario.
The only remain
Wiz
CVE-2022-50859 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50859 CVE-2022-50859 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50859 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: Fix the error length of VALIDATE_NEGOTIATE_INFO message
Commit d5c7076b772a ("smb3: add smb3.1.1 to default dialect list")
extend the dialects from 3 to 4, but forget to decrease the extended
length when specific the dialect, then the message length is larger
than expected.
This maybe leak some info through network because not initialize the
message body.
After apply this patch, the VALIDATE_NEGOTIATE_INFO message length is
reduced from 28 bytes to 26 bytes.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
C
Wiz
CVE-2026-25702 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.3
CVE-2026-25702 [HIGH] CVE-2026-25702 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-25702 :
Linux Kernel vulnerability analysis and mitigation
A Improper Access Control vulnerability in the kernel of SUSE SUSE Linux Enterprise Server 12 SP5 breaks nftables, causing firewall rules applied via nftables to not be effective.This issue affects SUSE Linux Enterprise Server: from 9e6d9d4601768c75fdb0bad3fbbe636e748939c2 before 9c294edb7085fb91650bc12233495a8974c5ff2d.
Source : NVD
## 9.8
Score
Published March 5, 2026
Severity CRITICAL
CNA Score 7.3
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 17.7
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-default-kgraft-devel
kernel-default-m
Wiz
CVE-2023-54210 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54210 CVE-2023-54210 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54210 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_remove_adv_monitor()
KASAN reports that there's a use-after-free in
hci_remove_adv_monitor(). Trawling through the disassembly, you can
see that the complaint is from the access in bt_dev_dbg() under the
HCI_ADV_MONITOR_EXT_MSFT case. The problem case happens because
msft_remove_monitor() can end up freeing the monitor
structure. Specifically:
hci_remove_adv_monitor() ->
msft_remove_monitor() ->
msft_remove_monitor_sync() ->
msft_le_cancel_monitor_advertisement_cb() ->
hci_free_adv_monitor()
Let's fix the problem by just stashing the relevant data when it's
still valid.
Source : NVD
Publish
Wiz
CVE-2025-68198 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68198 CVE-2025-68198 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68198 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crash: fix crashkernel resource shrink
When crashkernel is configured with a high reservation, shrinking its
value below the low crashkernel reservation causes two issues:
Invalid crashkernel resource objects
Kernel crash if crashkernel shrinking is done twice
For example, with crashkernel=200M,high, the kernel reserves 200MB of high
memory and some default low memory (say 256MB). The reservation appears
as:
cat /proc/iomem | grep -i crash
af000000-beffffff : Crash kernel
433000000-43f7fffff : Crash kernel
If crashkernel is then shrunk to 50MB (echo 52428800 >
/sys/kernel/kexec_crash_size), /proc/iomem still shows 256MB reserved:
af000000-befff
Wiz
CVE-2023-53856 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53856 CVE-2023-53856 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53856 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
of: overlay: Call of_changeset_init() early
When of_overlay_fdt_apply() fails, the changeset may be partially
applied, and the caller is still expected to call of_overlay_remove() to
clean up this partial state.
However, of_overlay_apply() calls of_resolve_phandles() before
init_overlay_changeset(). Hence if the overlay fails to apply due to an
unresolved symbol, the overlay_changeset.cset.entries list is still
uninitialized, and cleanup will crash with a NULL-pointer dereference in
overlay_removal_is_ok().
Fix this by moving the call to of_changeset_init() from
init_overlay_changeset() to of_overlay_fdt_apply(), where all other
early initializati
Wiz
CVE-2023-54067 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54067 CVE-2023-54067 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54067 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix race when deleting free space root from the dirty cow roots list
When deleting the free space tree we are deleting the free space root
from the list fs_info->dirty_cowonly_roots without taking the lock that
protects it, which is struct btrfs_fs_info::trans_lock.
This unsynchronized list manipulation may cause chaos if there's another
concurrent manipulation of this list, such as when adding a root to it
with ctree.c:add_root_to_dirty_list().
This can result in all sorts of weird failures caused by a race, such as
the following crash:
[337571.278245] general protection fault, probably for non-canonical address 0xdead000000000108: 0000 [#
Wiz
CVE-2026-23044 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23044 CVE-2026-23044 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23044 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PM: hibernate: Fix crash when freeing invalid crypto compressor
When crypto_alloc_acomp() fails, it returns an ERR_PTR value, not NULL.
The cleanup code in save_compressed_image() and load_compressed_image()
unconditionally calls crypto_free_acomp() without checking for ERR_PTR,
which causes crypto_acomp_tfm() to dereference an invalid pointer and
crash the kernel.
This can be triggered when the compression algorithm is unavailable
(e.g., CONFIG_CRYPTO_LZO not enabled).
Fix by adding IS_ERR_OR_NULL() checks before calling crypto_free_acomp()
and acomp_request_free(), similar to the existing kthread_stop() check.
[ rjw: Added 2 empty code lines ]
Wiz
CVE-2023-54161 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54161 CVE-2023-54161 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54161 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-modules
kernel-rt
Sources
NVD
Debian 11, 12, 13, 14 No Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 6, 7, 8, 9 Severity LOW No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Dec 26, 2025
## Get
Wiz
CVE-2023-54195 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54195 CVE-2023-54195 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54195 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rxrpc: Fix timeout of a call that hasn't yet been granted a channel
afs_make_call() calls rxrpc_kernel_begin_call() to begin a call (which may
get stalled in the background waiting for a connection to become
available); it then calls rxrpc_kernel_set_max_life() to set the timeouts -
but that starts the call timer so the call timer might then expire before
we get a connection assigned - leading to the following oops if the call
stalled:
BUG: kernel NULL pointer dereference, address: 0000000000000000
...
CPU: 1 PID: 5111 Comm: krxrpcio/0 Not tainted 6.3.0-rc7-build3+ #701
RIP: 0010:rxrpc_alloc_txbuf+0xc0/0x157
...
Call Trace:
rxrpc_send_ACK+0x50/0x1
Wiz
CVE-2026-23318 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23318 CVE-2026-23318 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23318 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: usb-audio: Use correct version for UAC3 header validation
The entry of the validators table for UAC3 AC header descriptor is
defined with the wrong protocol version UAC_VERSION_2, while it should
have been UAC_VERSION_3. This results in the validator never matching
for actual UAC3 devices (protocol == UAC_VERSION_3), causing their
header descriptors to bypass validation entirely. A malicious USB
device presenting a truncated UAC3 header could exploit this to cause
out-of-bounds reads when the driver later accesses unvalidated
descriptor fields.
The bug was introduced in the same commit as the recently fixed UAC3
feature unit sub-type typo, an
Wiz
CVE-2023-54304 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54304 CVE-2023-54304 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54304 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
firmware: meson_sm: fix to avoid potential NULL pointer dereference
of_match_device() may fail and returns a NULL pointer.
Fix this by checking the return value of of_match_device.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-5.15
kernel-devel-rt
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Ubuntu 16.
Wiz
CVE-2025-71226 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71226 CVE-2025-71226 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71226 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
## 7.1
Score
Published February 18, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-nvidia-6.14
linux-oracle-6.8
Sources
NVD
Debian 11, 12, 13 No Fix Added at: Feb 19, 2026
Debian 14 Has Fix Added at: Feb 19, 2026
Echo Has Fix Added at: Feb 19, 2026
Red Hat 8, 9, 10 Severity MEDIUM No Fix Added at: Feb 19, 2026
Ubuntu 16.04, 18.04, 20.04 S
Wiz
CVE-2026-31401 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31401 CVE-2026-31401 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31401 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: bpf: prevent buffer overflow in hid_hw_request
right now the returned value is considered to be always valid. However,
when playing with HID-BPF, the return value can be arbitrary big,
because it's the return value of dispatch_hid_bpf_raw_requests(), which
calls the struct_ops and we have no guarantees that the value makes
sense.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
Wiz
CVE-2026-23064 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23064 [MEDIUM] CVE-2026-23064 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23064 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: act_ife: avoid possible NULL deref
tcf_ife_encode() must make sure ife_encode() does not return NULL.
syzbot reported:
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:ife_tlv_meta_encode+0x41/0xa0 net/ife/ife.c:166
CPU: 3 UID: 0 PID: 8990 Comm: syz.0.696 Not tainted syzkaller #0 PREEMPT(full)
Call Trace: ife_encode_meta_u32+0x153/0x180 net/sched/act_ife.c:101
tcf_ife_encode net/sched/act_ife.c:841 [inline]
tcf_ife_act+0x1022/0x1de0 net/sched/act_ife.c:877
tc_act include/net/tc_wrapper.h:130 [i
Wiz
CVE-2023-54154 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54154 CVE-2023-54154 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54154 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: core: Fix target_cmd_counter leak
The target_cmd_counter struct allocated via target_alloc_cmd_counter() is
never freed, resulting in leaks across various transport types, e.g.:
unreferenced object 0xffff88801f920120 (size 96):
comm "sh", pid 102, jiffies 4294892535 (age 713.412s)
hex dump (first 32 bytes):
07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 38 01 92 1f 80 88 ff ff ........8.......
backtrace:
[] kmalloc_trace+0x11/0x20
[] target_alloc_cmd_counter+0x17/0x90 [target_core_mod]
[] target_setup_session+0x2d/0x140 [target_core_mod]
[] tcm_loop_tpg_nexus_store+0x19b/0x350 [tcm_loop]
[] co
Wiz
CVE-2026-23223 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23223 [HIGH] CVE-2026-23223 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23223 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: fix UAF in xchk_btree_check_block_owner
We cannot dereference bs->cur when trying to determine if bs->cur
aliases bs->sc->sa.{bno,rmap}_cur after the latter has been freed.
Fix this by sampling before type before any freeing could happen.
The correct temporal ordering was broken when we removed xfs_btnum_t.
Source : NVD
## 7.8
Score
Published February 18, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.3
Exploitation Probability (EPSS) N/A
Affected packages
Wiz
CVE-2023-54094 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54094 CVE-2023-54094 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54094 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: prevent skb corruption on frag list segmentation
Ian reported several skb corruptions triggered by rx-gro-list,
collecting different oops alike:
[ 62.624003] BUG: kernel NULL pointer dereference, address: 00000000000000c0
[ 62.631083] #PF: supervisor read access in kernel mode
[ 62.636312] #PF: error_code(0x0000) - not-present page
[ 62.641541] PGD 0 P4D 0
[ 62.644174] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 62.648629] CPU: 1 PID: 913 Comm: napi/eno2-79 Not tainted 6.4.0 #364
[ 62.655162] Hardware name: Supermicro Super Server/A2SDi-12C-HLN4F, BIOS 1.7a 10/13/2022
[ 62.663344] RIP: 0010:__udp_gso_segment (./include/linux/skbuff.h:2858
./include/li
Wiz
CVE-2023-54105 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54105 CVE-2023-54105 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54105 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: isotp: check CAN address family in isotp_bind()
Add missing check to block non-AF_CAN binds.
Syzbot created some code which matched the right sockaddr struct size
but used AF_XDP (0x2C) instead of AF_CAN (0x1D) in the address family
field:
bind$xdp(r2, &(0x7f0000000540)={0x2c, 0x0, r4, 0x0, r2}, 0x10)
^^^^
This has no funtional impact but the userspace should be notified about
the wrong address family field content.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabili
Wiz
CVE-2023-54241 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54241 CVE-2023-54241 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54241 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
MIPS: KVM: Fix NULL pointer dereference
After commit 45c7e8af4a5e3f0bea4ac209 ("MIPS: Remove KVM_TE support") we
get a NULL pointer dereference when creating a KVM guest:
[ 146.243409] Starting KVM with MIPS VZ extensions
[ 149.849151] CPU 3 Unable to handle kernel paging request at virtual address 0000000000000300, epc == ffffffffc06356ec, ra == ffffffffc063568c
[ 149.849177] Oops[#1]:
[ 149.849182] CPU: 3 PID: 2265 Comm: qemu-system-mip Not tainted 6.4.0-rc3+ #1671
[ 149.849188] Hardware name: THTF CX TL630 Series/THTF-LS3A4000-7A1000-ML4A, BIOS KL4.1F.TF.D.166.201225.R 12/25/2020
[ 149.849192] $ 0 : 0000000000000000 000000007400cce0 000000000040
Wiz
CVE-2025-71133 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71133 [HIGH] CVE-2025-71133 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71133 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/irdma: avoid invalid read in irdma_net_event
irdma_net_event() should not dereference anything from "neigh" (alias
"ptr") until it has checked that the event is NETEVENT_NEIGH_UPDATE.
Other events come with different structures pointed to by "ptr" and they
may be smaller than struct neighbour.
Move the read of neigh->dev under the NETEVENT_NEIGH_UPDATE case.
The bug is mostly harmless, but it triggers KASAN on debug kernels:
BUG: KASAN: stack-out-of-bounds in irdma_net_event+0x32e/0x3b0 [irdma]
Read of size 8 at addr ffffc900075e07f0 by task kworker/27:2/542554
CPU: 27 PID: 542554 Comm: kworker/27:2 Kdump: loaded Not tainted 5.14.0-630.el9.
Wiz
CVE-2023-54325 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54325 CVE-2023-54325 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54325 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: qat - fix out-of-bounds read
When preparing an AER-CTR request, the driver copies the key provided by
the user into a data structure that is accessible by the firmware.
If the target device is QAT GEN4, the key size is rounded up by 16 since
a rounded up size is expected by the device.
If the key size is rounded up before the copy, the size used for copying
the key might be bigger than the size of the region containing the key,
causing an out-of-bounds read.
Fix by doing the copy first and then update the keylen.
This is to fix the following warning reported by KASAN:
[ 138.150574] BUG: KASAN: global-out-of-bounds in qat_alg_skcipher_init
Wiz
CVE-2023-53995 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53995 CVE-2023-53995 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53995 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ipv4: fix one memleak in __inet_del_ifa()
I got the below warning when do fuzzing test:
unregister_netdevice: waiting for bond0 to become free. Usage count = 2
It can be repoduced via:
ip link add bond0 type bond
sysctl -w net.ipv4.conf.bond0.promote_secondaries=1
ip addr add 4.117.174.103/0 scope 0x40 dev bond0
ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0
ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0
ip addr del 4.117.174.103/0 scope 0x40 dev bond0
ip link delete bond0 type bond
In this reproduction test case, an incorrect 'last_prim' is found in
__inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x
Wiz
CVE-2026-23348 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23348 CVE-2026-23348 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23348 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cxl: Fix race of nvdimm_bus object when creating nvdimm objects
Found issue during running of cxl-translate.sh unit test. Adding a 3s
sleep right before the test seems to make the issue reproduce fairly
consistently. The cxl_translate module has dependency on cxl_acpi and
causes orphaned nvdimm objects to reprobe after cxl_acpi is removed.
The nvdimm_bus object is registered by the cxl_nvb object when
cxl_acpi_probe() is called. With the nvdimm_bus object missing,
__nd_device_register() will trigger NULL pointer dereference when
accessing the dev->parent that points to &nvdimm_bus->dev.
[ 192.884510] BUG: kernel NULL pointer dereference, address: 0
Wiz
CVE-2022-50786 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50786 CVE-2022-50786 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50786 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: s5p-mfc: Clear workbit to handle error condition
During error on CLOSE_INSTANCE command, ctx_work_bits was not getting
cleared. During consequent mfc execution NULL pointer dereferencing of
this context led to kernel panic. This patch fixes this issue by making
sure to clear ctx_work_bits always.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-raspi-5.4
kernel-d
Wiz
CVE-2026-23250 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23250 CVE-2026-23250 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23250 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: check return value of xchk_scrub_create_subord
Fix this function to return NULL instead of a mangled ENOMEM, then fix
the callers to actually check for a null pointer and return ENOMEM.
Most of the corrections here are for code merged between 6.2 and 6.10.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gcp-6.14
kernel-devel
Sources
NVD
Debian 13 No Fix Added at: M
Wiz
CVE-2025-68281 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68281 CVE-2025-68281 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68281 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: SDCA: bug fix while parsing mipi-sdca-control-cn-list
"struct sdca_control" declares "values" field as integer array.
But the memory allocated to it is of char array. This causes
crash for sdca_parse_function API. This patch addresses the
issue by allocating correct data size.
Source : NVD
## 5.7
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-ipaclone
Wiz
CVE-2025-40355 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40355 CVE-2025-40355 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40355 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sysfs: check visibility before changing group attribute ownership
Since commit 0c17270f9b92 ("net: sysfs: Implement is_visible for
phys_(port_id, port_name, switch_id)"), __dev_change_net_namespace() can
hit WARN_ON() when trying to change owner of a file that isn't visible.
See the trace below:
WARNING: CPU: 6 PID: 2938 at net/core/dev.c:12410 __dev_change_net_namespace+0xb89/0xc30
CPU: 6 UID: 0 PID: 2938 Comm: incusd Not tainted 6.17.1-1-mainline #1 PREEMPT(full) 4b783b4a638669fb644857f484487d17cb45ed1f
Hardware name: Framework Laptop 13 (AMD Ryzen 7040Series)/FRANMDCP07, BIOS 03.07 02/19/2025
RIP: 0010:__dev_change_net_namespace+0xb89/0xc30
[...
Wiz
CVE-2023-53866 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53866 CVE-2023-53866 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53866 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: soc-compress: Reposition and add pcm_mutex
If panic_on_warn is set and compress stream(DPCM) is started,
then kernel panic occurred because card->pcm_mutex isn't held appropriately.
In the following functions, warning were issued at this line
"snd_soc_dpcm_mutex_assert_held".
static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
struct snd_soc_pcm_runtime *be, int stream)
{
...
snd_soc_dpcm_mutex_assert_held(fe);
...
}
void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
{
...
snd_soc_dpcm_mutex_assert_held(fe);
...
}
void snd_soc_runtime_action(struct snd_soc_pcm_runtime *rtd,
int stream, int action)
{
...
snd_soc_dpcm_
Wiz
CVE-2026-23159 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23159 [MEDIUM] CVE-2026-23159 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23159 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf: sched: Fix perf crash with new is_user_task() helper
In order to do a user space stacktrace the current task needs to be a user
task that has executed in user space. It use to be possible to test if a
task is a user task or not by simply checking the task_struct mm field. If
it was non NULL, it was a user task and if not it was a kernel task.
But things have changed over time, and some kernel tasks now have their
own mm field.
An idea was made to instead test PF_KTHREAD and two functions were used to
wrap this check in case it became more complex to test if a task was a
user task or not[1]. But this was rejected and the C code simply checked
Wiz
CVE-2025-68192 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68192 CVE-2025-68192 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68192 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: qmi_wwan: initialize MAC header offset in qmimux_rx_fixup
Raw IP packets have no MAC header, leaving skb->mac_header uninitialized.
This can trigger kernel panics on ARM64 when xfrm or other subsystems
access the offset due to strict alignment checks.
Initialize the MAC header to prevent such crashes.
This can trigger kernel panics on ARM when running IPsec over the
qmimux0 interface.
Example trace:
Internal error: Oops: 000000009600004f [#1] SMP
CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.34-gbe78e49cb433 #1
Hardware name: LS1028A RDB Board (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : xfrm_input+
Wiz
CVE-2022-50757 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50757 CVE-2022-50757 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50757 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: camss: Clean up received buffers on failed start of streaming
It is required to return the received buffers, if streaming can not be
started. For instance media_pipeline_start() may fail with EPIPE, if
a link validation between entities is not passed, and in such a case
a user gets a kernel warning:
WARNING: CPU: 1 PID: 520 at drivers/media/common/videobuf2/videobuf2-core.c:1592 vb2_start_streaming+0xec/0x160 Call trace:
vb2_start_streaming+0xec/0x160
vb2_core_streamon+0x9c/0x1a0
vb2_ioctl_streamon+0x68/0xbc
v4l_streamon+0x30/0x3c
__video_do_ioctl+0x184/0x3e0
video_usercopy+0x37c/0x7b0
video_ioctl2+0x24/0x40
v4l2_ioctl+0x4c/0x70
The fix is
Wiz
CVE-2025-40341 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40341 CVE-2025-40341 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40341 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
futex: Don't leak robust_list pointer on exec race
sys_get_robust_list() and compat_get_robust_list() use ptrace_may_access()
to check if the calling task is allowed to access another task's
robust_list pointer. This check is racy against a concurrent exec() in the
target process.
During exec(), a task may transition from a non-privileged binary to a
privileged one (e.g., setuid binary) and its credentials/memory mappings
may change. If get_robust_list() performs ptrace_may_access() before
this transition, it may erroneously allow access to sensitive information
after the target becomes privileged.
A racy access allows an attacker to exploit a win
Wiz
CVE-2022-50698 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50698 CVE-2022-50698 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50698 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: da7219: Fix an error handling path in da7219_register_dai_clks()
If clk_hw_register() fails, the corresponding clk should not be
unregistered.
To handle errors from loops, clean up partial iterations before doing the
goto. So add a clk_hw_unregister().
Then use a while (--i >= 0) loop in the unwind section.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gkeop
li
Wiz
CVE-2025-68199 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68199 CVE-2025-68199 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68199 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
codetag: debug: handle existing CODETAG_EMPTY in mark_objexts_empty for slabobj_ext
When alloc_slab_obj_exts() fails and then later succeeds in allocating a
slab extension vector, it calls handle_failed_objexts_alloc() to mark all
objects in the vector as empty. As a result all objects in this slab
(slabA) will have their extensions set to CODETAG_EMPTY.
Later on if this slabA is used to allocate a slabobj_ext vector for
another slab (slabB), we end up with the slabB->obj_exts pointing to a
slabobj_ext vector that itself has a non-NULL slabobj_ext equal to
CODETAG_EMPTY. When slabB gets freed, free_slab_obj_exts() is called to
free slabB->obj_exts
Wiz
CVE-2026-23274 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23274 [HIGH] CVE-2026-23274 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23274 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels
IDLETIMER revision 0 rules reuse existing timers by label and always call
mod_timer() on timer->timer.
If the label was created first by revision 1 with XT_IDLETIMER_ALARM,
the object uses alarm timer semantics and timer->timer is never initialized.
Reusing that object from revision 0 causes mod_timer() on an uninitialized
timer_list, triggering debugobjects warnings and possible panic when
panic_on_warn=1.
Fix this by rejecting revision 0 rule insertion when an existing timer with
the same label is of ALARM type.
Source : NVD
## 7.8
Score
Published March 20, 2026
Severity HIG
Wiz
CVE-2025-68297 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68297 CVE-2025-68297 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68297 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ceph: fix crash in process_v2_sparse_read() for encrypted directories
The crash in process_v2_sparse_read() for fscrypt-encrypted directories
has been reported. Issue takes place for Ceph msgr2 protocol in secure
mode. It can be reproduced by the steps:
sudo mount -t ceph :/ /mnt/cephfs/ -o name=admin,fs=cephfs,ms_mode=secure
(1) mkdir /mnt/cephfs/fscrypt-test-3
(2) cp area_decrypted.tar /mnt/cephfs/fscrypt-test-3
(3) fscrypt encrypt --source=raw_key --key=./my.key /mnt/cephfs/fscrypt-test-3
(4) fscrypt lock /mnt/cephfs/fscrypt-test-3
(5) fscrypt unlock --key=my.key /mnt/cephfs/fscrypt-test-3
(6) cat /mnt/cephfs/fscrypt-test-3/area_decrypted.tar
(
Wiz
CVE-2026-23114 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23114 [MEDIUM] CVE-2026-23114 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23114 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64/fpsimd: ptrace: Fix SVE writes on !SME systems
When SVE is supported but SME is not supported, a ptrace write to the
NT_ARM_SVE regset can place the tracee into an invalid state where
(non-streaming) SVE register data is stored in FP_STATE_SVE format but
TIF_SVE is clear. This can result in a later warning from
fpsimd_restore_current_state(), e.g.
WARNING: CPU: 0 PID: 7214 at arch/arm64/kernel/fpsimd.c:383 fpsimd_restore_current_state+0x50c/0x748
When this happens, fpsimd_restore_current_state() will set TIF_SVE,
placing the task into the correct state. This occurs before any other
check of TIF_SVE can possibly occur, as other checks of TIF_
Wiz
CVE-2026-23188 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23188 [MEDIUM] CVE-2026-23188 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23188 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: r8152: fix resume reset deadlock
rtl8152 can trigger device reset during reset which
potentially can result in a deadlock:
**** DPM device timeout after 10 seconds; 15 seconds until panic ****
Call Trace: schedule+0x483/0x1370
schedule_preempt_disabled+0x15/0x30
__mutex_lock_common+0x1fd/0x470
__rtl8152_set_mac_address+0x80/0x1f0
dev_set_mac_address+0x7f/0x150
rtl8152_post_reset+0x72/0x150
usb_reset_device+0x1d0/0x220
rtl8152_resume+0x99/0xc0
usb_resume_interface+0x3e/0xc0
usb_resume_both+0x104/0x150
usb_resume+0x22/0x110
The problem is that rtl8152 resume calls reset under
tp->control mutex while reset basically re-enters rtl8152
and at
Wiz
CVE-2023-54047 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54047 CVE-2023-54047 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54047 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/rockchip: dw_hdmi: cleanup drm encoder during unbind
This fixes a use-after-free crash during rmmod.
The DRM encoder is embedded inside the larger rockchip_hdmi,
which is allocated with the component. The component memory
gets freed before the main drm device is destroyed. Fix it
by running encoder cleanup before tearing down its container.
[moved encoder cleanup above clk_disable, similar to bind-error-path]
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perce
Wiz
CVE-2023-54062 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54062 CVE-2023-54062 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54062 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix invalid free tracking in ext4_xattr_move_to_block()
In ext4_xattr_move_to_block(), the value of the extended attribute
which we need to move to an external block may be allocated by
kvmalloc() if the value is stored in an external inode. So at the end
of the function the code tried to check if this was the case by
testing entry->e_value_inum.
However, at this point, the pointer to the xattr entry is no longer
valid, because it was removed from the original location where it had
been stored. So we could end up calling kvfree() on a pointer which
was not allocated by kvmalloc(); or we could also potentially leak
memory by not freeing the bu
Wiz
CVE-2023-54030 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54030 CVE-2023-54030 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54030 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/net: don't overflow multishot recv
Don't allow overflowing multishot recv CQEs, it might get out of
hand, hurt performance, and in the worst case scenario OOM the task.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-arm
dtb-marvell
Sources
NVD
Debian 12 No Fix Added at: Dec 26, 2025
Debian 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26,
Wiz
CVE-2023-54209 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54209 CVE-2023-54209 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54209 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: fix blktrace debugfs entries leakage
Commit 99d055b4fd4b ("block: remove per-disk debugfs files in
blk_unregister_queue") moves blk_trace_shutdown() from
blk_release_queue() to blk_unregister_queue(), this is safe if blktrace
is created through sysfs, however, there is a regression in corner
case.
blktrace can still be enabled after del_gendisk() through ioctl if
the disk is opened before del_gendisk(), and if blktrace is not shutdown
through ioctl before closing the disk, debugfs entries will be leaked.
Fix this problem by shutdown blktrace in disk_release(), this is safe
because blk_trace_remove() is reentrant.
Source : NVD
Published De
Wiz
CVE-2026-23401 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23401 CVE-2026-23401 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23401 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE
When installing an emulated MMIO SPTE, do so after dropping/zapping the
existing SPTE (if it's shadow-present). While commit a54aa15c6bda3 was
right about it being impossible to convert a shadow-present SPTE to an
MMIO SPTE due to a guest write, it failed to account for writes to guest
memory that are outside the scope of KVM.
E.g. if host userspace modifies a shadowed gPTE to switch from a memslot
to emulted MMIO and then the guest hits a relevant page fault, KVM will
install the MMIO SPTE without first zapping the shadow-present SPTE.
------------[ cut here ]-----------
Wiz
CVE-2022-50836 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50836 CVE-2022-50836 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50836 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
remoteproc: sysmon: fix memory leak in qcom_add_sysmon_subdev()
The kfree() should be called when of_irq_get_byname() fails or
devm_request_threaded_irq() fails in qcom_add_sysmon_subdev(),
otherwise there will be a memory leak, so add kfree() to fix it.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-fips
dlm-kmp-default
Sources
NVD
Debian 11, 12, 13, 14 Has
Wiz
CVE-2025-68799 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68799 CVE-2025-68799 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68799 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
caif: fix integer underflow in cffrml_receive()
The cffrml_receive() function extracts a length field from the packet
header and, when FCS is disabled, subtracts 2 from this length without
validating that len >= 2.
If an attacker sends a malicious packet with a length field of 0 or 1
to an interface with FCS disabled, the subtraction causes an integer
underflow.
This can lead to memory exhaustion and kernel instability, potential
information disclosure if padding contains uninitialized kernel memory.
Fix this by validating that len >= 2 before performing the subtraction.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technolog
Wiz
CVE-2025-68350 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68350 CVE-2025-68350 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68350 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
exfat: fix divide-by-zero in exfat_allocate_bitmap
The variable max_ra_count can be 0 in exfat_allocate_bitmap(),
which causes a divide-by-zero error in the subsequent modulo operation
(i % max_ra_count), leading to a system crash.
When max_ra_count is 0, it means that readahead is not used. This patch
load the bitmap without readahead.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-
Wiz
CVE-2025-68244 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68244 CVE-2025-68244 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68244 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915: Avoid lock inversion when pinning to GGTT on CHV/BXT+VTD
On completion of i915_vma_pin_ww(), a synchronous variant of
dma_fence_work_commit() is called. When pinning a VMA to GGTT address
space on a Cherry View family processor, or on a Broxton generation SoC
with VTD enabled, i.e., when stop_machine() is then called from
intel_ggtt_bind_vma(), that can potentially lead to lock inversion among
reservation_ww and cpu_hotplug locks.
[86.861179] ======================================================
[86.861193] WARNING: possible circular locking dependency detected
[86.861209] 6.15.0-rc5-CI_DRM_16515-gca0305cadc2d+ #1 Tainted: G U
[86.861226
Wiz
CVE-2023-54041 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54041 CVE-2023-54041 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54041 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring: fix memory leak when removing provided buffers
When removing provided buffers, io_buffer structs are not being disposed
of, leading to a memory leak. They can't be freed individually, because
they are allocated in page-sized groups. They need to be added to some
free list instead, such as io_buffers_cache. All callers already hold
the lock protecting it, apart from when destroying buffers, so had to
extend the lock there.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2025-68209 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68209 CVE-2025-68209 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68209 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mlx5: Fix default values in create CQ
Currently, CQs without a completion function are assigned the
mlx5_add_cq_to_tasklet function by default. This is problematic since
only user CQs created through the mlx5_ib driver are intended to use
this function.
Additionally, all CQs that will use doorbells instead of polling for
completions must call mlx5_cq_arm. However, the default CQ creation flow
leaves a valid value in the CQ's arm_db field, allowing FW to send
interrupts to polling-only CQs in certain corner cases.
These two factors would allow a polling-only kernel CQ to be triggered
by an EQ interrupt and call a completion function intended only f
Wiz
CVE-2025-68233 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68233 CVE-2025-68233 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68233 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/tegra: Add call to put_pid()
Add a call to put_pid() corresponding to get_task_pid().
host1x_memory_context_alloc() does not take ownership of the PID so we
need to free it here to avoid leaking.
[[email protected]: reword commit message]
Source : NVD
## 5.7
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 11.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel
kernel-abi-stablelists
Sources
NVD
De
Wiz
CVE-2026-23059 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23059 CVE-2026-23059 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23059 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Sanitize payload size to prevent member overflow
In qla27xx_copy_fpin_pkt() and qla27xx_copy_multiple_pkt(), the frame_size
reported by firmware is used to calculate the copy length into
item->iocb. However, the iocb member is defined as a fixed-size 64-byte
array within struct purex_item.
If the reported frame_size exceeds 64 bytes, subsequent memcpy calls will
overflow the iocb member boundary. While extra memory might be allocated,
this cross-member write is unsafe and triggers warnings under
CONFIG_FORTIFY_SOURCE.
Fix this by capping total_bytes to the size of the iocb member (64 bytes)
before allocation and copying. This ensure
Wiz
CVE-2026-23219 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23219 [MEDIUM] CVE-2026-23219 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23219 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/slab: Add alloc_tagging_slab_free_hook for memcg_alloc_abort_single
When CONFIG_MEM_ALLOC_PROFILING_DEBUG is enabled, the following warning
may be noticed:
[ 3959.023862] ------------[ cut here ]------------
[ 3959.023891] alloc_tag was not cleared (got tag for lib/xarray.c:378)
[ 3959.023947] WARNING: ./include/linux/alloc_tag.h:155 at alloc_tag_add+0x128/0x178, CPU#6: mkfs.ntfs/113998
[ 3959.023978] Modules linked in: dns_resolver tun brd overlay exfat btrfs blake2b libblake2b xor xor_neon raid6_pq loop sctp ip6_udp_tunnel udp_tunnel ext4 crc16 mbcache jbd2 rfkill sunrpc vfat fat sg fuse nfnetlink sr_mod virtio_gpu cdrom drm_client_lib virtio_
Wiz
CVE-2025-68179 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68179 CVE-2025-68179 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68179 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390: Disable ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
As reported by Luiz Capitulino enabling HVO on s390 leads to reproducible
crashes. The problem is that kernel page tables are modified without
flushing corresponding TLB entries.
Even if it looks like the empty flush_tlb_all() implementation on s390 is
the problem, it is actually a different problem: on s390 it is not allowed
to replace an active/valid page table entry with another valid page table
entry without the detour over an invalid entry. A direct replacement may
lead to random crashes and/or data corruption.
In order to invalidate an entry special instructions have to be used
(e.g. ipte or i
Wiz
CVE-2023-54107 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54107 CVE-2023-54107 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54107 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blk-cgroup: dropping parent refcount after pd_free_fn() is done
Some cgroup policies will access parent pd through child pd even
after pd_offline_fn() is done. If pd_free_fn() for parent is called
before child, then UAF can be triggered. Hence it's better to guarantee
the order of pd_free_fn().
Currently refcount of parent blkg is dropped in __blkg_release(), which
is before pd_free_fn() is called in blkg_free_work_fn() while
blkg_free_work_fn() is called asynchronously.
This patch make sure pd_free_fn() called from removing cgroup is ordered
by delaying dropping parent refcount after calling pd_free_fn() for
child.
BTW, pd_free_fn() will also be
Wiz
CVE-2025-68725 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68725 [MEDIUM] CVE-2025-68725 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68725 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Do not let BPF test infra emit invalid GSO types to stack
Yinhao et al. reported that their fuzzer tool was able to trigger a
skb_warn_bad_offload() from netif_skb_features() -> gso_features_check().
When a BPF program - triggered via BPF test infra - pushes the packet
to the loopback device via bpf_clone_redirect() then mentioned offload
warning can be seen. GSO-related features are then rightfully disabled.
We get into this situation due to convert___skb_to_skb() setting
gso_segs and gso_size but not gso_type. Technically, it makes sense
that this warning triggers since the GSO properties are malformed due
to the gso_type. Potentially, the g
Wiz
CVE-2026-23255 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23255 CVE-2026-23255 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23255 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: add proper RCU protection to /proc/net/ptype
Yin Fengwei reported an RCU stall in ptype_seq_show() and provided
a patch.
Real issue is that ptype_seq_next() and ptype_seq_show() violate
RCU rules.
ptype_seq_show() runs under rcu_read_lock(), and reads pt->dev
to get device name without any barrier.
At the same time, concurrent writers can remove a packet_type structure
(which is correctly freed after an RCU grace period) and clear pt->dev
without an RCU grace period.
Define ptype_iter_state to carry a dev pointer along seq_net_private:
struct ptype_iter_state {
struct seq_net_private p;
struct net_device *dev; // added in this patch
};
We
Wiz
CVE-2023-54016 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54016 CVE-2023-54016 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54016 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath12k: Fix memory leak in rx_desc and tx_desc
Currently when ath12k_dp_cc_desc_init() is called we allocate
memory to rx_descs and tx_descs. In ath12k_dp_cc_cleanup(), during
descriptor cleanup rx_descs and tx_descs memory is not freed.
This is cause of memory leak. These allocated memory should be
freed in ath12k_dp_cc_cleanup.
In ath12k_dp_cc_desc_init(), we can save base address of rx_descs
and tx_descs. In ath12k_dp_cc_cleanup(), we can free rx_descs and
tx_descs memory using their base address.
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Tec
Wiz
CVE-2026-23149 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23149 [MEDIUM] CVE-2026-23149 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23149 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm: Do not allow userspace to trigger kernel warnings in drm_gem_change_handle_ioctl()
Since GEM bo handles are u32 in the uapi and the internal implementation
uses idr_alloc() which uses int ranges, passing a new handle larger than
INT_MAX trivially triggers a kernel warning:
idr_alloc():
...
if (WARN_ON_ONCE(start < 0))
return -EINVAL;
...
Fix it by rejecting new handles above INT_MAX and at the same time make
the end limit calculation more obvious by moving into int domain.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has C
Wiz
CVE-2026-23246 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.8
CVE-2026-23246 [HIGH] CVE-2026-23246 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23246 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration
link_id is taken from the ML Reconfiguration element (control & 0x000f),
so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS
(15) elements, so index 15 is out-of-bounds. Skip subelements with
link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds
write.
Source : NVD
## 8.8
Score
Published March 18, 2026
Severity HIGH
CNA Score 8.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.5
Exploitation
Wiz
CVE-2026-23224 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23224 [HIGH] CVE-2026-23224 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23224 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: fix UAF issue for file-backed mounts w/ directio option
[ 9.269940][ T3222] Call trace:
[ 9.269948][ T3222] ext4_file_read_iter+0xac/0x108
[ 9.269979][ T3222] vfs_iocb_iter_read+0xac/0x198
[ 9.269993][ T3222] erofs_fileio_rq_submit+0x12c/0x180
[ 9.270008][ T3222] erofs_fileio_submit_bio+0x14/0x24
[ 9.270030][ T3222] z_erofs_runqueue+0x834/0x8ac
[ 9.270054][ T3222] z_erofs_read_folio+0x120/0x220
[ 9.270083][ T3222] filemap_read_folio+0x60/0x120
[ 9.270102][ T3222] filemap_fault+0xcac/0x1060
[ 9.270119][ T3222] do_pte_missing+0x2d8/0x1554
[ 9.270131][ T3222] handle_mm_fault+0x5ec/0x70c
[ 9.270142][ T3222] do_page_fault+0x178/0x88c
[ 9.270167][
Wiz
CVE-2026-23147 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23147 [MEDIUM] CVE-2026-23147 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23147 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: zlib: fix the folio leak on S390 hardware acceleration
[BUG]
After commit aa60fe12b4f4 ("btrfs: zlib: refactor S390x HW acceleration
buffer preparation"), we no longer release the folio of the page cache
of folio returned by btrfs_compress_filemap_get_folio() for S390
hardware acceleration path.
[CAUSE]
Before that commit, we call kumap_local() and folio_put() after handling
each folio.
Although the timing is not ideal (it release previous folio at the
beginning of the loop, and rely on some extra cleanup out of the loop),
it at least handles the folio release correctly.
Meanwhile the refactored code is easier to read, it lacks the call to
Wiz
CVE-2026-23017 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23017 [MEDIUM] CVE-2026-23017 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23017 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix error handling in the init_task on load
If the init_task fails during a driver load, we end up without vports and
netdevs, effectively failing the entire process. In that state a
subsequent reset will result in a crash as the service task attempts to
access uninitialized resources. Following trace is from an error in the
init_task where the CREATE_VPORT (op 501) is rejected by the FW:
[40922.763136] idpf 0000:83:00.0: Device HW Reset initiated
[40924.449797] idpf 0000:83:00.0: Transaction failed (op 501)
[40958.148190] idpf 0000:83:00.0: HW reset detected
[40958.161202] BUG: kernel NULL pointer dereference, address: 00000000000000a8
...
[
Wiz
CVE-2026-23335 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23335 CVE-2026-23335 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23335 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah()
struct irdma_create_ah_resp { // 8 bytes, no padding
__u32 ah_id; // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx)
__u8 rsvd[4]; // offset 4 - NEVER SET <- LEAK
};
rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata().
The reserved members of the structure were not zeroed.
Source : NVD
## 7.1
Score
Published March 25, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabili
Wiz
CVE-2023-54242 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54242 CVE-2023-54242 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54242 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block, bfq: Fix division by zero error on zero wsum
When the weighted sum is zero the calculation of limit causes
a division by zero error. Fix this by continuing to the next level.
This was discovered by running as root:
stress-ng --ioprio 0
Fixes divison by error oops:
[ 521.450556] divide error: 0000 [#1] SMP NOPTI
[ 521.450766] CPU: 2 PID: 2684464 Comm: stress-ng-iopri Not tainted 6.2.1-1280.native #1
[ 521.451117] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
[ 521.451627] RIP: 0010:bfqq_request_over_limit+0x207/0x400
[ 521.451875] Code: 01 48 8d 0c c8 74 0b 48 8b 82 98 0
Wiz
CVE-2023-54221 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54221 CVE-2023-54221 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54221 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clk: imx93: fix memory leak and missing unwind goto in imx93_clocks_probe
In function probe(), it returns directly without unregistered hws
when error occurs.
Fix this by adding 'goto unregister_hws;' on line 295 and
line 310.
Use devm_kzalloc() instead of kzalloc() to automatically
free the memory using devm_kfree() when error occurs.
Replace of_iomap() with devm_of_iomap() to automatically
handle the unused ioremap region and delete 'iounmap(anatop_base);'
in unregister_hws.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Relea
Wiz
CVE-2026-23119 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23119 [MEDIUM] CVE-2026-23119 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23119 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bonding: provide a net pointer to __skb_flow_dissect()
After 3cbf4ffba5ee ("net: plumb network namespace into __skb_flow_dissect")
we have to provide a net pointer to __skb_flow_dissect(),
either via skb->dev, skb->sk, or a user provided pointer.
In the following case, syzbot was able to cook a bare skb.
WARNING: net/core/flow_dissector.c:1131 at __skb_flow_dissect+0xb57/0x68b0 net/core/flow_dissector.c:1131, CPU#1: syz.2.1418/11053
Call Trace: bond_flow_dissect drivers/net/bonding/bond_main.c:4093 [inline]
__bond_xmit_hash+0x2d7/0xba0 drivers/net/bonding/bond_main.c:4157
bond_xmit_hash_xdp drivers/net/bonding/bond_main.c:4208 [inline]
bond_xdp_xm
Wiz
CVE-2023-54255 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54255 CVE-2023-54255 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54255 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sh: dma: Fix DMA channel offset calculation
Various SoCs of the SH3, SH4 and SH4A family, which use this driver,
feature a differing number of DMA channels, which can be distributed
between up to two DMAC modules. The existing implementation fails to
correctly accommodate for all those variations, resulting in wrong
channel offset calculations and leading to kernel panics.
Rewrite dma_base_addr() in order to properly calculate channel offsets
in a DMAC module. Fix dmaor_read_reg() and dmaor_write_reg(), so that
the correct DMAC module base is selected for the DMAOR register.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Techno
Wiz
CVE-2026-23096 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23096 [MEDIUM] CVE-2026-23096 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23096 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
uacce: fix cdev handling in the cleanup path
When cdev_device_add fails, it internally releases the cdev memory,
and if cdev_device_del is then executed, it will cause a hang error.
To fix it, we check the return value of cdev_device_add() and clear
uacce->cdev to avoid calling cdev_device_del in the uacce_remove.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2023-54015 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54015 CVE-2023-54015 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54015 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5: Devcom, fix error flow in mlx5_devcom_register_device
In case devcom allocation is failed, mlx5 is always freeing the priv.
However, this priv might have been allocated by a different thread,
and freeing it might lead to use-after-free bugs.
Fix it by freeing the priv only in case it was allocated by the
running thread.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
Wiz
CVE-2026-31404 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31404 CVE-2026-31404 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31404 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSD: Defer sub-object cleanup in export put callbacks
svc_export_put() calls path_put() and auth_domain_put() immediately
when the last reference drops, before the RCU grace period. RCU
readers in e_show() and c_show() access both ex_path (via
seq_path/d_path) and ex_client->name (via seq_escape) without
holding a reference. If cache_clean removes the entry and drops the
last reference concurrently, the sub-objects are freed while still
in use, producing a NULL pointer dereference in d_path.
Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or
ex_stats") moved kfree of ex_uuid and ex_stats into the
call_rcu callback, but left path_put() and
Wiz
CVE-2026-23023 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23023 [MEDIUM] CVE-2026-23023 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23023 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix memory leak in idpf_vport_rel()
Free vport->rx_ptype_lkup in idpf_vport_rel() to avoid leaking memory
during a reset. Reported by kmemleak:
unreferenced object 0xff450acac838a000 (size 4096):
comm "kworker/u258:5", pid 7732, jiffies 4296830044
hex dump (first 32 bytes):
00 00 00 00 00 10 00 00 00 10 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 10 00 00 00 00 00 00 ................
backtrace (crc 3da81902):
__kmalloc_cache_noprof+0x469/0x7a0
idpf_send_get_rx_ptype_msg+0x90/0x570 [idpf]
idpf_init_task+0x1ec/0x8d0 [idpf]
process_one_work+0x226/0x6d0
worker_thread+0x19e/0x340
kthread+0x10f/0x250
ret_from_fork+0x251/0x2b0
ret_
Wiz
CVE-2025-68308 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68308 CVE-2025-68308 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68308 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: kvaser_usb: leaf: Fix potential infinite loop in command parsers
kvaser_usb_leaf_wait_cmd()
kvaser_usb_leaf_read_bulk_callback
pos
round_up()
pos
round_up
pos
pos
pos + 1
pos
pos + 1
round_up()
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 12.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-livepatch-6_4_0-150700_53_28-default
kernel-rt-64k-debug-modules-core
Sources
Wiz
CVE-2026-23122 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23122 [MEDIUM] CVE-2026-23122 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23122 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
igc: Reduce TSN TX packet buffer from 7KB to 5KB per queue
The previous 7 KB per queue caused TX unit hangs under heavy
timestamping load. Reducing to 5 KB avoids these hangs and matches
the TSN recommendation in I225/I226 SW User Manual Section 7.5.4.
The 8 KB "freed" by this change is currently unused. This reduction
is not expected to impact throughput, as the i226 is PCIe-limited
for small TSN packets rather than TX-buffer-limited.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/
Wiz
CVE-2026-23380 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23380 CVE-2026-23380 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23380 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Fix WARN_ON in tracing_buffers_mmap_close
When a process forks, the child process copies the parent's VMAs but the
user_mapped reference count is not incremented. As a result, when both the
parent and child processes exit, tracing_buffers_mmap_close() is called
twice. On the second call, user_mapped is already 0, causing the function to
return -ENODEV and triggering a WARN_ON.
Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set.
But this is only a hint, and the application can call
madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the
application does that, it can trigger this issue on fork.
Fix it by
Wiz
CVE-2022-50823 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50823 CVE-2022-50823 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50823 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clk: tegra: Fix refcount leak in tegra114_clock_init
of_find_matching_node() returns a node pointer with refcount
incremented, we should use of_node_put() on it when not need anymore.
Add missing of_node_put() to avoid refcount leak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-debug-modules-core
kernel-source
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added a
Wiz
CVE-2022-50860 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50860 CVE-2022-50860 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50860 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
apparmor: Fix memleak in alloc_ns()
After changes in commit a1bd627b46d1 ("apparmor: share profile name on
replacement"), the hname member of struct aa_policy is not valid slab
object, but a subset of that, it can not be freed by kfree_sensitive(),
use aa_policy_destroy() to fix it.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg
kernel-devel
Sources
NVD
D
Wiz
CVE-2022-50830 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50830 CVE-2022-50830 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50830 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
auxdisplay: hd44780: Fix potential memory leak in hd44780_remove()
hd44780_probe() allocates a memory chunk for hd with kzalloc() and
makes "lcd->drvdata->hd44780" point to it. When we call hd44780_remove(),
we should release all relevant memory and resource. But "lcd->drvdata
->hd44780" is not released, which will lead to a memory leak.
We should release the "lcd->drvdata->hd44780" in hd44780_remove() to fix
the memory leak bug.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation P
Wiz
CVE-2026-22993 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22993 [MEDIUM] CVE-2026-22993 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22993 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: Fix RSS LUT NULL ptr issue after soft reset
During soft reset, the RSS LUT is freed and not restored unless the
interface is up. If an ethtool command that accesses the rss lut is
attempted immediately after reset, it will result in NULL ptr
dereference. Also, there is no need to reset the rss lut if the soft reset
does not involve queue count change.
After soft reset, set the RSS LUT to default values based on the updated
queue count only if the reset was a result of a queue count change and
the LUT was not configured by the user. In all other cases, don't touch
the LUT.
Steps to reproduce:
** Bring the interface down (if up)
ifconfig eth1
Wiz
CVE-2023-54127 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54127 CVE-2023-54127 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54127 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/jfs: prevent double-free in dbUnmount() after failed jfs_remount()
## Syzkaller reported the following issue:
BUG: KASAN: double-free in slab_free mm/slub.c:3787 [inline]
BUG: KASAN: double-free in __kmem_cache_free+0x71/0x110 mm/slub.c:3800
Free of addr ffff888086408000 by task syz-executor.4/12750
[...]
Call Trace: [...]
kasan_report_invalid_free+0xac/0xd0 mm/kasan/report.c:482
____kasan_slab_free+0xfb/0x120
kasan_slab_free include/linux/kasan.h:177 [inline]
slab_free_hook mm/slub.c:1781 [inline]
slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1807
slab_free mm/slub.c:3787 [inline]
__kmem_cache_free+0x71/0x110 mm/slub.c:3800
dbUnmount+0xf4/0x1
Wiz
CVE-2025-40357 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40357 CVE-2025-40357 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40357 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/smc: fix general protection fault in __smc_diag_dump
The syzbot report a crash:
Oops: general protection fault, probably for non-canonical address 0xfbd5a5d5a0000003: 0000 [#1] SMP KASAN NOPTI
KASAN: maybe wild-memory-access in range [0xdead4ead00000018-0xdead4ead0000001f]
CPU: 1 UID: 0 PID: 6949 Comm: syz.0.335 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025
RIP: 0010:smc_diag_msg_common_fill net/smc/smc_diag.c:44 [inline]
RIP: 0010:__smc_diag_dump.constprop.0+0x3ca/0x2550 net/smc/smc_diag.c:89
Call Trace: smc_diag_dump_proto+0x26d/0x420 net/smc/smc_diag.c:217
smc_diag_d
Wiz
CVE-2025-71080 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71080 [MEDIUM] CVE-2025-71080 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71080 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: fix a BUG in rt6_get_pcpu_route() under PREEMPT_RT
On PREEMPT_RT kernels, after rt6_get_pcpu_route() returns NULL, the
current task can be preempted. Another task running on the same CPU
may then execute rt6_make_pcpu_route() and successfully install a
pcpu_rt entry. When the first task resumes execution, its cmpxchg()
in rt6_make_pcpu_route() will fail because rt6i_pcpu is no longer
NULL, triggering the BUG_ON(prev). It's easy to reproduce it by adding
mdelay() after rt6_get_pcpu_route().
Using preempt_disable/enable is not appropriate here because
ip6_rt_pcpu_alloc() may sleep.
Fix this by handling the cmpxchg() failure gracefully on PREEM
Wiz
CVE-2026-23366 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23366 CVE-2026-23366 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23366 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/client: Do not destroy NULL modes
'modes' in drm_client_modeset_probe may fail to kcalloc. If this
occurs, we jump to 'out', calling modes_destroy on it, which
dereferences it. This may result in a NULL pointer dereference in the
error case. Prevent that.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel
kernel-64k-modules-extra
Sources
NVD
Debian 14 Has Fix Added at
Wiz
CVE-2025-68364 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68364 CVE-2025-68364 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68364 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ocfs2: relax BUG() to ocfs2_error() in __ocfs2_move_extent()
In '__ocfs2_move_extent()', relax 'BUG()' to 'ocfs2_error()' just
to avoid crashing the whole kernel due to a filesystem corruption.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
linux-aws
linux-azure-6.14
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo
Wiz
CVE-2026-23186 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23186 [MEDIUM] CVE-2026-23186 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23186 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hwmon: (acpi_power_meter) Fix deadlocks related to acpi_power_meter_notify()
The acpi_power_meter driver's .notify() callback function,
acpi_power_meter_notify(), calls hwmon_device_unregister() under a lock
that is also acquired by callbacks in sysfs attributes of the device
being unregistered which is prone to deadlocks between sysfs access and
device removal.
Address this by moving the hwmon device removal in
acpi_power_meter_notify() outside the lock in question, but notice
that doing it alone is not sufficient because two concurrent
METER_NOTIFY_CONFIG notifications may be attempting to remove the
same device at the same time. To prevent that
Wiz
CVE-2022-50844 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50844 CVE-2022-50844 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50844 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: Fix type of second parameter in odn_edit_dpm_table() callback
With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
proposed warning in clang aims to catch these at compile time, which
reveals:
drivers/gpu/drm/amd/amdgpu/../pm/swsmu/amdgpu_smu.c:3008:29: error: incompatible function pointer types initializing 'int (*)(void *, uint32_t, long , uint
Wiz
CVE-2022-50780 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50780 CVE-2022-50780 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50780 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: fix UAF issue in nfqnl_nf_hook_drop() when ops_init() failed
When the ops_init() interface is invoked to initialize the net, but
ops->init() fails, data is released. However, the ptr pointer in
net->gen is invalid. In this case, when nfqnl_nf_hook_drop() is invoked
to release the net, invalid address access occurs.
The process is as follows:
setup_net()
ops_init()
data = kzalloc(...) ---> alloc "data"
net_assign_generic() ---> assign "date" to ptr in net->gen
...
ops->init() ---> failed
...
kfree(data); ---> ptr in net->gen is invalid
...
ops_exit_list()
...
nfqnl_nf_hook_drop()
*q = nfnl_queue_pernet(net) ---> q is invalid
The following is
Wiz
CVE-2026-23450 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23450 CVE-2026-23450 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23450 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/smc: fix NULL dereference and UAF in smc_tcp_syn_recv_sock()
Syzkaller reported a panic in smc_tcp_syn_recv_sock() [1].
smc_tcp_syn_recv_sock() is called in the TCP receive path
(softirq) via icsk_af_ops->syn_recv_sock on the clcsock (TCP
listening socket). It reads sk_user_data to get the smc_sock
pointer. However, when the SMC listen socket is being closed
concurrently, smc_close_active() sets clcsock->sk_user_data
to NULL under sk_callback_lock, and then the smc_sock itself
can be freed via sock_put() in smc_release().
This leads to two issues:
NULL pointer dereference: sk_user_data is NULL when
accessed.
Use-after-free: sk_user_data is r
Wiz
CVE-2022-50824 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50824 CVE-2022-50824 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50824 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tpm: tpm_tis: Add the missed acpi_put_table() to fix memory leak
In check_acpi_tpm2(), we get the TPM2 table just to make
sure the table is there, not used after the init, so the
acpi_put_table() should be added to release the ACPI memory.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-default-livepatch
kernel-core
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added a
Wiz
CVE-2022-50825 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50825 CVE-2022-50825 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50825 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: typec: wusb3801: fix fwnode refcount leak in wusb3801_probe()
I got the following report while doing fault injection test:
OF: ERROR: memory leak, expected refcount 1 instead of 4,
of_node_get()/of_node_put() unbalanced - destroy cset entry:
attach overlay node /i2c/tcpc@60/connector
If wusb3801_hw_init() fails, fwnode_handle_put() needs be called to
avoid refcount leak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probabi
Wiz
CVE-2026-23088 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23088 [MEDIUM] CVE-2026-23088 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23088 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Fix crash on synthetic stacktrace field usage
When creating a synthetic event based on an existing synthetic event that
had a stacktrace field and the new synthetic event used that field a
kernel crash occurred:
~# cd /sys/kernel/tracing
~# echo 's:stack unsigned long stack[];' > dynamic_events
~# echo 'hist:keys=prev_pid:s0=common_stacktrace if prev_state & 3' >> events/sched/sched_switch/trigger
~# echo 'hist:keys=next_pid:s1=$s0:onmatch(sched.sched_switch).trace(stack,$s1)' >> events/sched/sched_switch/trigger
The above creates a synthetic event that takes a stacktrace when a task
schedules out in a non-running state and passes that st
Wiz
CVE-2023-53825 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53825 CVE-2023-53825 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53825 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
kcm: Fix error handling for SOCK_DGRAM in kcm_sendmsg().
syzkaller found a memory leak in kcm_sendmsg(), and commit c821a88bd720
("kcm: Fix memory leak in error path of kcm_sendmsg()") suppressed it by
updating kcm_tx_msg(head)->last_skb if partial data is copied so that the
following sendmsg() will resume from the skb.
However, we cannot know how many bytes were copied when we get the error.
Thus, we could mess up the MSG_MORE queue.
When kcm_sendmsg() fails for SOCK_DGRAM, we should purge the queue as we
do so for UDP by udp_flush_pending_frames().
Even without this change, when the error occurred, the following sendmsg()
resumed from a wrong s
Wiz
CVE-2025-68200 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68200 CVE-2025-68200 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68200 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Add bpf_prog_run_data_pointers()
syzbot found that cls_bpf_classify() is able to change
tc_skb_cb(skb)->drop_reason triggering a warning in sk_skb_reason_drop().
WARNING: CPU: 0 PID: 5965 at net/core/skbuff.c:1192 __sk_skb_reason_drop net/core/skbuff.c:1189 [inline]
WARNING: CPU: 0 PID: 5965 at net/core/skbuff.c:1192 sk_skb_reason_drop+0x76/0x170 net/core/skbuff.c:1214
struct tc_skb_cb has been added in commit ec624fe740b4 ("net/sched:
Extend qdisc control block with tc control block"), which added a wrong
interaction with db58ba459202 ("bpf: wire in data and data_end for
cls_act_bpf").
drop_reason was added later.
Add bpf_prog_run_data_poi
Wiz
CVE-2025-40347 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40347 CVE-2025-40347 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40347 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: enetc: fix the deadlock of enetc_mdio_lock
After applying the workaround for err050089, the LS1028A platform
experiences RCU stalls on RT kernel. This issue is caused by the
recursive acquisition of the read lock enetc_mdio_lock. Here list some
of the call stacks identified under the enetc_poll path that may lead to
a deadlock:
enetc_poll
-> enetc_lock_mdio
-> enetc_clean_rx_ring OR napi_complete_done
-> napi_gro_receive
-> enetc_start_xmit
-> enetc_lock_mdio
-> enetc_map_tx_buffs
-> enetc_unlock_mdio
-> enetc_unlock_mdio
After enetc_poll acquires the read lock, a higher-priority writer attempts
to acquire the lock, causing preemption. The wr
Wiz
CVE-2025-68284 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68284 CVE-2025-68284 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68284 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: prevent potential out-of-bounds writes in handle_auth_session_key()
The len field originates from untrusted network packets. Boundary
checks have been added to prevent potential out-of-bounds writes when
decrypting the connection secret or processing service tickets.
[ idryomov: changelog ]
Source : NVD
## 7
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
Wiz
CVE-2026-22991 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22991 [MEDIUM] CVE-2026-22991 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22991 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: make free_choose_arg_map() resilient to partial allocation
free_choose_arg_map() may dereference a NULL pointer if its caller fails
after a partial allocation.
For example, in decode_choose_args(), if allocation of arg_map->args
fails, execution jumps to the fail label and free_choose_arg_map() is
called. Since arg_map->size is updated to a non-zero value before memory
allocation, free_choose_arg_map() will iterate over arg_map->args and
dereference a NULL pointer.
To prevent this potential NULL pointer dereference and make
free_choose_arg_map() more resilient, add checks for pointers before
iterating.
Source : NVD
## 5.5
Score
Publ
Wiz
CVE-2023-54091 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54091 CVE-2023-54091 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54091 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/client: Fix memory leak in drm_client_target_cloned
dmt_mode is allocated and never freed in this function.
It was found with the ast driver, but most drivers using generic fbdev
setup are probably affected.
This fixes the following kmemleak report:
backtrace:
[] drm_mode_duplicate+0x45/0x220 [drm]
[] drm_client_target_cloned.constprop.0+0x27b/0x480 [drm]
[] drm_client_modeset_probe+0x6bd/0xf50 [drm]
[] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper]
[] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper]
[] drm_client_register+0x169/0x240 [drm]
[] ast_pci_probe+0x142/0x190 [ast]
[] local_pci_probe+0xdc/0x180
[] work_for_
Wiz
CVE-2023-54089 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54089 CVE-2023-54089 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54089 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
virtio_pmem: add the missing REQ_OP_WRITE for flush bio
When doing mkfs.xfs on a pmem device, the following warning was
------------[ cut here ]------------
WARNING: CPU: 2 PID: 384 at block/blk-core.c:751 submit_bio_noacct
Modules linked in:
CPU: 2 PID: 384 Comm: mkfs.xfs Not tainted 6.4.0-rc7+ #154
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
RIP: 0010:submit_bio_noacct+0x340/0x520
......
Call Trace: ? submit_bio_noacct+0xd5/0x520
submit_bio+0x37/0x60
async_pmem_flush+0x79/0xa0
nvdimm_flush+0x17/0x40
pmem_submit_bio+0x370/0x390
__submit_bio+0xbc/0x190
submit_bio_noacct_nocheck+0x14d/0x370
submit_bio_noacct+0x1ef/0x520
submit_bio+0x55/0x6
Wiz
CVE-2025-13350 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-13350 [HIGH] CVE-2025-13350 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-13350 :
Linux Ubuntu vulnerability analysis and mitigation
Ubuntu Linux 6.8 GA retains the legacy AF_UNIX garbage collector but backports upstream commit 8594d9b85c07 ("af_unix: Don’t call skb_get() for OOB skb"). When orphaned MSG_OOB sockets hit unix_gc(), the garbage collector still calls kfree_skb() as if OOB SKBs held two references; on Ubuntu Linux 6.8 (Noble Numbat) kernel tree, they have only the queue reference, so the buffer is freed while still reachable and subsequent queue walks dereference freed memory, yielding a reliable local privilege escalation (LPE) caused by a use-after-free (UAF). Ubuntu builds that have already taken the new GC stack from commit 4090fa373f0e, and mainline Linux kernels shipping that infrastructure are unaffected because they no longer e
Wiz
CVE-2026-23163 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23163 [MEDIUM] CVE-2026-23163 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23163 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: fix NULL pointer dereference in amdgpu_gmc_filter_faults_remove
On APUs such as Raven and Renoir (GC 9.1.0, 9.2.2, 9.3.0), the ih1 and
ih2 interrupt ring buffers are not initialized. This is by design, as
these secondary IH rings are only available on discrete GPUs. See
vega10_ih_sw_init() which explicitly skips ih1/ih2 initialization when
AMD_IS_APU is set.
However, amdgpu_gmc_filter_faults_remove() unconditionally uses ih1 to
get the timestamp of the last interrupt entry. When retry faults are
enabled on APUs (noretry=0), this function is called from the SVM page
fault recovery path, resulting in a NULL pointer dereference when
amdgpu
Wiz
CVE-2024-14027 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2024-14027 CVE-2024-14027 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2024-14027 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/xattr: missing fdput() in fremovexattr error path
In the Linux kernel, the fremovexattr() syscall calls fdget() to acquire a
file reference but returns early without calling fdput() when
strncpy_from_user() fails on the name argument. In multi-threaded processes
where fdget() takes the slow path, this permanently leaks one
file reference per call, pinning the struct file and associated kernel
objects in memory. An unprivileged local user can exploit this to cause
kernel memory exhaustion. The issue was inadvertently fixed by commit
a71874379ec8 ("xattr: switch to CLASS(fd)").
Source : NVD
## 5.5
Score
Published March 9, 2026
Severity MEDIU
Wiz
CVE-2026-22992 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22992 [MEDIUM] CVE-2026-22992 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22992 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: return the handler error from mon_handle_auth_done()
Currently any error from ceph_auth_handle_reply_done() is propagated
via finish_auth() but isn't returned from mon_handle_auth_done(). This
results in higher layers learning that (despite the monitor considering
us to be successfully authenticated) something went wrong in the
authentication phase and reacting accordingly, but msgr2 still trying
to proceed with establishing the session in the background. In the
case of secure mode this can trigger a WARN in setup_crypto() and later
lead to a NULL pointer dereference inside of prepare_auth_signature().
Source : NVD
## 5.5
Score
Publis
Wiz
CVE-2025-71068 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71068 [HIGH] CVE-2025-71068 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71068 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
svcrdma: bound check rq_pages index in inline path
svc_rdma_copy_inline_range indexed rqstp->rq_pages[rc_curpage] without
verifying rc_curpage stays within the allocated page array. Add guards
before the first use and after advancing to a new page.
Source : NVD
## 7.8
Score
Published January 13, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-debug-modules-wireless
linux-gcp-6.14
S
Wiz
CVE-2025-68740 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68740 CVE-2025-68740 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68740 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ima: Handle error code returned by ima_filter_rule_match()
In ima_match_rules(), if ima_filter_rule_match() returns -ENOENT due to
the rule being NULL, the function incorrectly skips the 'if (!rc)' check
and sets 'result = true'. The LSM rule is considered a match, causing
extra files to be measured by IMA.
This issue can be reproduced in the following scenario:
After unloading the SELinux policy module via 'semodule -d', if an IMA
measurement is triggered before ima_lsm_rules is updated,
in ima_match_rules(), the first call to ima_filter_rule_match() returns
-ESTALE. This causes the code to enter the 'if (rc == -ESTALE &&
!rule_reinitialized)' blo
Wiz
CVE-2026-22985 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22985 [MEDIUM] CVE-2026-22985 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22985 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: Fix RSS LUT NULL pointer crash on early ethtool operations
The RSS LUT is not initialized until the interface comes up, causing
the following NULL pointer crash when ethtool operations like rxhash on/off
are performed before the interface is brought up for the first time.
Move RSS LUT initialization from ndo_open to vport creation to ensure LUT
is always available. This enables RSS configuration via ethtool before
bringing the interface up. Simplify LUT management by maintaining all
changes in the driver's soft copy and programming zeros to the indirection
table when rxhash is disabled. Defer HW programming until the interface
comes up if it
Wiz
CVE-2023-54122 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54122 CVE-2023-54122 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54122 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/dpu: Add check for cstate
As kzalloc may fail and return NULL pointer,
it should be better to check cstate
in order to avoid the NULL pointer dereference
in __drm_atomic_helper_crtc_reset.
Patchwork: https://patchwork.freedesktop.org/patch/514163/
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-hwe-5.15
linux-iot
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Ad
Wiz
CVE-2025-68181 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68181 CVE-2025-68181 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68181 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/radeon: Remove calls to drm_put_dev()
Since the allocation of the drivers main structure was changed to
devm_drm_dev_alloc() drm_put_dev()'ing to trigger it to be free'd
should be done by devres.
However, drm_put_dev() is still in the probe error and device remove
paths. When the driver fails to probe warnings like the following are
shown because devres is trying to drm_put_dev() after the driver
already did it.
[ 5.642230] radeon 0000:01:05.0: probe with driver radeon failed with error -22
[ 5.649605] ------------[ cut here ]------------
[ 5.649607] refcount_t: underflow; use-after-free.
[ 5.649620] WARNING: CPU: 0 PID: 357 at lib/refcount.c:
Wiz
CVE-2023-54243 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54243 CVE-2023-54243 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54243 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: ebtables: fix table blob use-after-free
We are not allowed to return an error at this point.
Looking at the code it looks like ret is always 0 at this
point, but its not.
t = find_table_lock(net, repl->name, &ret, &ebt_mutex);
... this can return a valid table, with ret != 0.
This bug causes update of table->private with the new
blob, but then frees the blob right away in the caller.
Syzbot report:
BUG: KASAN: vmalloc-out-of-bounds in __ebt_unregister_table+0xc00/0xcd0 net/bridge/netfilter/ebtables.c:1168
Read of size 4 at addr ffffc90005425000 by task kworker/u4:4/74
Workqueue: netns cleanup_net
Call Trace:
kasan_report+0xbf/0x1f0 m
Wiz
CVE-2022-50885 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50885 CVE-2022-50885 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50885 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failed
There is a null-ptr-deref when mount.cifs over rdma:
BUG: KASAN: null-ptr-deref in rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe]
Read of size 8 at addr 0000000000000018 by task mount.cifs/3046
CPU: 2 PID: 3046 Comm: mount.cifs Not tainted 6.1.0-rc5+ #62
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc3
Call Trace: dump_stack_lvl+0x34/0x44
kasan_report+0xad/0x130
rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe]
execute_in_process_context+0x25/0x90
__rxe_cleanup+0x101/0x1d0 [rdma_rxe]
rxe_create_qp+0x16a/0x180 [rdma_rxe]
create_qp.part.0+0x27d/0x340
ib_create_qp_
Wiz
CVE-2025-71119 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71119 [MEDIUM] CVE-2025-71119 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71119 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/kexec: Enable SMT before waking offline CPUs
If SMT is disabled or a partial SMT state is enabled, when a new kernel
image is loaded for kexec, on reboot the following warning is observed:
kexec: Waking offline cpu 228.
WARNING: CPU: 0 PID: 9062 at arch/powerpc/kexec/core_64.c:223 kexec_prepare_cpus+0x1b0/0x1bc
[snip]
NIP kexec_prepare_cpus+0x1b0/0x1bc
LR kexec_prepare_cpus+0x1a0/0x1bc
Call Trace:
kexec_prepare_cpus+0x1a0/0x1bc (unreliable)
default_machine_kexec+0x160/0x19c
machine_kexec+0x80/0x88
kernel_kexec+0xd0/0x118
__do_sys_reboot+0x210/0x2c4
system_call_exception+0x124/0x320
system_call_vectored_common+0x15c/0x2ec
This occurs as add
Wiz
CVE-2026-23072 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23072 [MEDIUM] CVE-2026-23072 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23072 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
l2tp: Fix memleak in l2tp_udp_encap_recv().
syzbot reported memleak of struct l2tp_session, l2tp_tunnel,
sock, etc. [0]
The cited commit moved down the validation of the protocol
version in l2tp_udp_encap_recv().
The new place requires an extra error handling to avoid the
memleak.
Let's call l2tp_session_put() there.
[0]:
BUG: memory leak
unreferenced object 0xffff88810a290200 (size 512):
comm "syz.0.17", pid 6086, jiffies 4294944299
hex dump (first 32 bytes):
7d eb 04 0c 00 00 00 00 01 00 00 00 00 00 00 00 }...............
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace (crc babb6a4f):
kmemleak_alloc_recursive include
Wiz
CVE-2023-54073 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54073 CVE-2023-54073 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54073 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tpm: Add !tpm_amd_is_rng_defective() to the hwrng_unregister() call site
The following crash was reported:
[ 1950.279393] list_del corruption, ffff99560d485790->next is NULL
[ 1950.279400] ------------[ cut here ]------------
[ 1950.279401] kernel BUG at lib/list_debug.c:49!
[ 1950.279405] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 1950.279407] CPU: 11 PID: 5886 Comm: modprobe Tainted: G O 6.2.8_1 #1
[ 1950.279409] Hardware name: Gigabyte Technology Co., Ltd. B550M AORUS PRO-P/B550M AORUS PRO-P,
BIOS F15c 05/11/2022
[ 1950.279410] RIP: 0010:__list_del_entry_valid+0x59/0xc0
[ 1950.279415] Code: 48 8b 01 48 39 f8 75 5a 48 8b 72 08 48 39 c6 75 65 b
Wiz
CVE-2025-68375 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68375 CVE-2025-68375 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68375 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/x86: Fix NULL event access and potential PEBS record loss
When intel_pmu_drain_pebs_icl() is called to drain PEBS records, the
perf_event_overflow() could be called to process the last PEBS record.
While perf_event_overflow() could trigger the interrupt throttle and
stop all events of the group, like what the below call-chain shows.
perf_event_overflow()
-> __perf_event_overflow()
->__perf_event_account_interrupt()
-> perf_event_throttle_group()
-> perf_event_throttle()
-> event->pmu->stop()
-> x86_pmu_stop()
The side effect of stopping the events is that all corresponding event
pointers in cpuc->events[] array are cleared to NULL.
Assume t
Wiz
CVE-2022-50773 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50773 CVE-2022-50773 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50773 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: mts64: fix possible null-ptr-defer in snd_mts64_interrupt
I got a null-ptr-defer error report when I do the following tests
on the qemu platform:
make defconfig and CONFIG_PARPORT=m, CONFIG_PARPORT_PC=m,
CONFIG_SND_MTS64=m
Then making test scripts:
cat>test_mod1.sh<<EOF
modprobe snd-mts64
modprobe snd-mts64
EOF
Executing the script, perhaps several times, we will get a null-ptr-defer
report, as follow:
syzkaller:~# ./test_mod.sh
snd_mts64: probe of snd_mts64.0 failed with error -5
modprobe: ERROR: could not insert 'snd_mts64': No such device
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor write access in ker
Wiz
CVE-2023-54027 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54027 CVE-2023-54027 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54027 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iio: core: Prevent invalid memory access when there is no parent
Commit 813665564b3d ("iio: core: Convert to use firmware node handle
instead of OF node") switched the kind of nodes to use for label
retrieval in device registration. Probably an unwanted change in that
commit was that if the device has no parent then NULL pointer is
accessed. This is what happens in the stock IIO dummy driver when a
new entry is created in configfs:
## mkdir /sys/kernel/config/iio/devices/dummy/foo
BUG: kernel NULL pointer dereference, address: ...
...
Call Trace:
__iio_device_register
iio_dummy_probe
Since there seems to be no reason to make a parent device of
Wiz
CVE-2025-68779 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68779 CVE-2025-68779 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68779 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Avoid unregistering PSP twice
PSP is unregistered twice in:
_mlx5e_remove -> mlx5e_psp_unregister
mlx5e_nic_cleanup -> mlx5e_psp_unregister
This leads to a refcount underflow in some conditions:
------------[ cut here ]------------
refcount_t: underflow; use-after-free.
WARNING: CPU: 2 PID: 1694 at lib/refcount.c:28 refcount_warn_saturate+0xd8/0xe0
[...]
mlx5e_psp_unregister+0x26/0x50 [mlx5_core]
mlx5e_nic_cleanup+0x26/0x90 [mlx5_core]
mlx5e_remove+0xe6/0x1f0 [mlx5_core]
auxiliary_bus_remove+0x18/0x30
device_release_driver_internal+0x194/0x1f0
bus_remove_device+0xc6/0x130
device_del+0x159/0x3c0
mlx5_rescan_drivers_locked+0xbc/0x2a0 [mlx5
Wiz
CVE-2026-23195 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.0
CVE-2026-23195 [HIGH] CVE-2026-23195 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23195 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cgroup/dmem: avoid pool UAF
An UAF issue was observed:
BUG: KASAN: slab-use-after-free in page_counter_uncharge+0x65/0x150
Write of size 8 at addr ffff888106715440 by task insmod/527
CPU: 4 UID: 0 PID: 527 Comm: insmod 6.19.0-rc7-next-20260129+ #11
Tainted: [O]=OOT_MODULE
Call Trace: dump_stack_lvl+0x82/0xd0
kasan_report+0xca/0x100
kasan_check_range+0x39/0x1c0
page_counter_uncharge+0x65/0x150
dmem_cgroup_uncharge+0x1f/0x260
Allocated by task 527:
Freed by task 0:
The buggy address belongs to the object at ffff888106715400
which belongs to the cache kmalloc-512 of size 512
The buggy address is located 64 bytes inside of
freed 512-byte region [ff
Wiz
CVE-2025-68344 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68344 CVE-2025-68344 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68344 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: wavefront: Fix integer overflow in sample size validation
The wavefront_send_sample() function has an integer overflow issue
when validating sample size. The header->size field is u32 but gets
cast to int for comparison with dev->freemem
Fix by using unsigned comparison to avoid integer overflow.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and li
Wiz
CVE-2025-68331 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68331 CVE-2025-68331 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68331 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: uas: fix urb unmapping issue when the uas device is remove during ongoing data transfer
When a UAS device is unplugged during data transfer, there is
a probability of a system panic occurring. The root cause is
an access to an invalid memory address during URB callback handling.
Specifically, this happens when the dma_direct_unmap_sg() function
is called within the usb_hcd_unmap_urb_for_dma() interface, but the
sg->dma_address field is 0 and the sg data structure has already been
freed.
The SCSI driver sends transfer commands by invoking uas_queuecommand_lck()
in uas.c, using the uas_submit_urbs() function to submit requests to USB.
Within the
Wiz
CVE-2023-54323 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54323 CVE-2023-54323 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54323 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cxl/pmem: Fix nvdimm registration races
A loop of the form:
while true; do modprobe cxl_pci; modprobe -r cxl_pci; done
...fails with the following crash signature:
BUG: kernel NULL pointer dereference, address: 0000000000000040
[..]
RIP: 0010:cxl_internal_send_cmd+0x5/0xb0 [cxl_core]
[..]
Call Trace:
cxl_pmem_ctl+0x121/0x240 [cxl_pmem]
nvdimm_get_config_data+0xd6/0x1a0 [libnvdimm]
nd_label_data_init+0x135/0x7e0 [libnvdimm]
nvdimm_probe+0xd6/0x1c0 [libnvdimm]
nvdimm_bus_probe+0x7a/0x1e0 [libnvdimm]
really_probe+0xde/0x380
__driver_probe_device+0x78/0x170
driver_probe_device+0x1f/0x90
__device_attach_driver+0x85/0x110
bus_for_each_drv+0x7d/0xc0
__
Wiz
CVE-2025-71236 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71236 [MEDIUM] CVE-2025-71236 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71236 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Validate sp before freeing associated memory
System crash with the following signature
[154563.214890] nvme nvme2: NVME-FC{1}: controller connect complete
[154564.169363] qla2xxx [0000:b0:00.1]-3002:2: nvme: Sched: Set ZIO exchange threshold to 3.
[154564.169405] qla2xxx [0000:b0:00.1]-ffffff:2: SET ZIO Activity exchange threshold to 5.
[154565.539974] qla2xxx [0000:b0:00.1]-5013:2: RSCN database changed – 0078 0080 0000.
[154565.545744] qla2xxx [0000:b0:00.1]-5013:2: RSCN database changed – 0078 00a0 0000.
[154565.545857] qla2xxx [0000:b0:00.1]-11a2:2: FEC=enabled (data rate).
[154565.552760] qla2xxx [0000:b0:00.1]-11a2:2: FEC=enable
Wiz
CVE-2025-68377 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68377 CVE-2025-68377 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68377 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ns: initialize ns_list_node for initial namespaces
Make sure that the list is always initialized for initial namespaces.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Dec 26, 2025
## Get a CVE risk assessment
Get a prioritized view of CVEs in your cloud—so you can focus on what'
Wiz
CVE-2026-23154 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23154 [MEDIUM] CVE-2026-23154 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23154 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: fix segmentation of forwarding fraglist GRO
This patch enhances GSO segment handling by properly checking
the SKB_GSO_DODGY flag for frag_list GSO packets, addressing
low throughput issues observed when a station accesses IPv4
servers via hotspots with an IPv6-only upstream interface.
Specifically, it fixes a bug in GSO segmentation when forwarding
GRO packets containing a frag_list. The function skb_segment_list
cannot correctly process GRO skbs that have been converted by XLAT,
since XLAT only translates the header of the head skb. Consequently,
skbs in the frag_list may remain untranslated, resulting in protocol
inconsistencies and reduced
Wiz
CVE-2023-54123 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54123 CVE-2023-54123 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54123 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid10: fix memleak for 'conf->bio_split'
In the error path of raid10_run(), 'conf' need be freed, however,
'conf->bio_split' is missed and memory will be leaked.
Since there are 3 places to free 'conf', factor out a helper to fix the
problem.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-internal
kernel-cross-headers
Sources
NVD
Debian 11, 12, 13
Wiz
CVE-2025-68802 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68802 CVE-2025-68802 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68802 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe: Limit num_syncs to prevent oversized allocations
The exec and vm_bind ioctl allow userspace to specify an arbitrary
num_syncs value. Without bounds checking, a very large num_syncs
can force an excessively large allocation, leading to kernel warnings
from the page allocator as below.
Introduce DRM_XE_MAX_SYNCS (set to 1024) and reject any request
exceeding this limit.
"
------------[ cut here ]------------
WARNING: CPU: 0 PID: 1217 at mm/page_alloc.c:5124 __alloc_frozen_pages_noprof+0x2f8/0x2180 mm/page_alloc.c:5124
...
Call Trace: alloc_pages_mpol+0xe4/0x330 mm/mempolicy.c:2416
___kmalloc_large_node+0xd8/0x110 mm/slub.c:4317
__kmalloc_lar
Wiz
CVE-2025-71147 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71147 [MEDIUM] CVE-2025-71147 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71147 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KEYS: trusted: Fix a memory leak in tpm2_load_cmd
'tpm2_load_cmd' allocates a tempoary blob indirectly via 'tpm2_key_decode'
but it is not freed in the failure paths. Address this by wrapping the blob
into with a cleanup helper.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-devel-matched
kernel-rt-64k-devel
Sources
NVD
CBL
Wiz
CVE-2023-54270 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54270 CVE-2023-54270 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54270 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: usb: siano: Fix use after free bugs caused by do_submit_urb
There are UAF bugs caused by do_submit_urb(). One of the KASan reports
is shown below:
[ 36.403605] BUG: KASAN: use-after-free in worker_thread+0x4a2/0x890
[ 36.406105] Read of size 8 at addr ffff8880059600e8 by task kworker/0:2/49
[ 36.408316]
[ 36.408867] CPU: 0 PID: 49 Comm: kworker/0:2 Not tainted 6.2.0-rc3-15798-g5a41237ad1d4-dir8
[ 36.411696] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g15584
[ 36.416157] Workqueue: 0x0 (events)
[ 36.417654] Call Trace:
[ 36.418546] [ 36.419320] dump_stack_lvl+0x96/0xd0
[ 36.420522] print_address_description+0x75/0
Wiz
CVE-2023-54190 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54190 CVE-2023-54190 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54190 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
leds: led-core: Fix refcount leak in of_led_get()
class_find_device_by_of_node() calls class_find_device(), it will take
the reference, use the put_device() to drop the reference when not need
anymore.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
perf
python-perf
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red H
Wiz
CVE-2025-68204 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68204 CVE-2025-68204 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68204 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pmdomain: arm: scmi: Fix genpd leak on provider registration failure
If of_genpd_add_provider_onecell() fails during probe, the previously
created generic power domains are not removed, leading to a memory leak
and potential kernel crash later in genpd_debug_add().
Add proper error handling to unwind the initialized domains before
returning from probe to ensure all resources are correctly released on
failure.
Example crash trace observed without this fix:
| Unable to handle kernel paging request at virtual address fffffffffffffc70
| CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.18.0-rc1 #405 PREEMPT
| Hardware name: ARM LTD ARM Juno Developm
Wiz
CVE-2026-23343 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23343 CVE-2026-23343 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23343 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xdp: produce a warning when calculated tailroom is negative
Many ethernet drivers report xdp Rx queue frag size as being the same as
DMA write size. However, the only user of this field, namely
bpf_xdp_frags_increase_tail(), clearly expects a truesize.
Such difference leads to unspecific memory corruption issues under certain
circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when
running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses
all DMA-writable space in 2 buffers. This would be fine, if only
rxq->frag_size was properly set to 4K, but value of 3K results in a
negative tailroom, because there is a non-zero pa
Wiz
CVE-2023-53987 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53987 CVE-2023-53987 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53987 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ping: Fix potentail NULL deref for /proc/net/icmp.
After commit dbca1596bbb0 ("ping: convert to RCU lookups, get rid
of rwlock"), we use RCU for ping sockets, but we should use spinlock
for /proc/net/icmp to avoid a potential NULL deref mentioned in
the previous patch.
Let's go back to using spinlock there.
Note we can convert ping sockets to use hlist instead of hlist_nulls
because we do not use SLAB_TYPESAFE_BY_RCU for ping sockets.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploita
Wiz
CVE-2023-54148 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54148 CVE-2023-54148 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54148 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Move representor neigh cleanup to profile cleanup_tx
For IP tunnel encapsulation in ECMP (Equal-Cost Multipath) mode, as
the flow is duplicated to the peer eswitch, the related neighbour
information on the peer uplink representor is created as well.
In the cited commit, eswitch devcom unpair is moved to uplink unload
API, specifically the profile->cleanup_tx. If there is a encap rule
offloaded in ECMP mode, when one eswitch does unpair (because of
unloading the driver, for instance), and the peer rule from the peer
eswitch is going to be deleted, the use-after-free error is triggered
while accessing neigh info, as it is already cleaned u
Wiz
CVE-2023-54217 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54217 CVE-2023-54217 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54217 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Revert "drm/msm: Add missing check and destroy for alloc_ordered_workqueue"
This reverts commit 643b7d0869cc7f1f7a5ac7ca6bd25d88f54e31d0.
A recent patch that tried to fix up the msm_drm_init() paths with
respect to the workqueue but only ended up making things worse:
First, the newly added calls to msm_drm_uninit() on early errors would
trigger NULL-pointer dereferences, for example, as the kms pointer would
not have been initialised. (Note that these paths were also modified by
a second broken error handling patch which in effect cancelled out this
part when merged.)
Second, the newly added allocation sanity check would still leak the
previously
Wiz
CVE-2026-31408 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31408 CVE-2026-31408 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31408 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold
sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately
releases the lock without holding a reference to the socket. A concurrent
close() can free the socket between the lock release and the subsequent
sk->sk_state access, resulting in a use-after-free.
Other functions in the same file (sco_sock_timeout(), sco_conn_del())
correctly use sco_sock_hold() to safely hold a reference under the lock.
Fix by using sco_sock_hold() to take a reference before releasing the
lock, and adding sock_put() on all exit paths.
Source : NVD
## 7.8
Score
Published April
Wiz
CVE-2025-40327 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40327 CVE-2025-40327 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40327 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/core: Fix system hang caused by cpu-clock usage
cpu-clock usage by the async-profiler tool can trigger a system hang,
which got bisected back to the following commit by Octavia Togami:
18dbcbfabfff ("perf: Fix the POLL_HUP delivery breakage") causes this issue
The root cause of the hang is that cpu-clock is a special type of SW
event which relies on hrtimers. The __perf_event_overflow() callback
is invoked from the hrtimer handler for cpu-clock events, and
__perf_event_overflow() tries to call cpu_clock_event_stop()
to stop the event, which calls htimer_cancel() to cancel the hrtimer.
But that's a recursion into the hrtimer code from a hrtim
Wiz
CVE-2022-50772 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50772 CVE-2022-50772 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50772 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netdevsim: fix memory leak in nsim_bus_dev_new()
If device_register() failed in nsim_bus_dev_new(), the value of reference
in nsim_bus_dev->dev is 1. obj->name in nsim_bus_dev->dev will not be
released.
unreferenced object 0xffff88810352c480 (size 16):
comm "echo", pid 5691, jiffies 4294945921 (age 133.270s)
hex dump (first 16 bytes):
6e 65 74 64 65 76 73 69 6d 31 00 00 00 00 00 00 netdevsim1......
backtrace:
[] __kmalloc_node_track_caller+0x3a/0xb0
[] kvasprintf+0xc3/0x160
[] kvasprintf_const+0x55/0x180
[] kobject_set_name_vargs+0x56/0x150
[] dev_set_name+0xbb/0xf0
[] device_add+0x1f8/0x1cb0
[] new_device_store+0x3b6/0x5e0
[] bus_attr_store+0x72/0
Wiz
CVE-2022-50828 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50828 CVE-2022-50828 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50828 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clk: zynqmp: Fix stack-out-of-bounds in strncpy`
"BUG: KASAN: stack-out-of-bounds in strncpy+0x30/0x68"
Linux-ATF interface is using 16 bytes of SMC payload. In case clock name is
longer than 15 bytes, string terminated NULL character will not be received
by Linux. Add explicit NULL character at last byte to fix issues when clock
name is longer.
This fixes below bug reported by KASAN:
BUG: KASAN: stack-out-of-bounds in strncpy+0x30/0x68
Read of size 1 at addr ffff0008c89a7410 by task swapper/0/1
CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.4.0-00396-g81ef9e7-dirty #3
Hardware name: Xilinx Versal vck190 Eval board revA (QSPI) (DT)
Call trace:
dump
Wiz
CVE-2025-40340 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40340 CVE-2025-40340 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40340 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe: Fix oops in xe_gem_fault when running core_hotunplug test.
I saw an oops in xe_gem_fault when running the xe-fast-feedback
testlist against the realtime kernel without debug options enabled.
The panic happens after core_hotunplug unbind-rebind finishes.
Presumably what happens is that a process mmaps, unlocks because
of the FAULT_FLAG_RETRY_NOWAIT logic, has no process memory left,
causing ttm_bo_vm_dummy_page() to return VM_FAULT_NOPAGE, since
there was nothing left to populate, and then oopses in
"mem_type_is_vram(tbo->resource->mem_type)" because tbo->resource
is NULL.
It's convoluted, but fits the data and explains the oops after
the t
Wiz
CVE-2023-54170 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54170 CVE-2023-54170 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54170 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
keys: Fix linking a duplicate key to a keyring's assoc_array
When making a DNS query inside the kernel using dns_query(), the request
code can in rare cases end up creating a duplicate index key in the
assoc_array of the destination keyring. It is eventually found by
a BUG_ON() check in the assoc_array implementation and results in
a crash.
Example report:
[2158499.700025] kernel BUG at ../lib/assoc_array.c:652!
[2158499.700039] invalid opcode: 0000 [#1] SMP PTI
[2158499.700065] CPU: 3 PID: 31985 Comm: kworker/3:1 Kdump: loaded Not tainted 5.3.18-150300.59.90-default #1 SLE15-SP3
[2158499.700096] Hardware name: VMware, Inc. VMware Virtual Platform/
Wiz
CVE-2022-50715 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50715 CVE-2022-50715 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50715 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid1: stop mdx_raid1 thread when raid1 array run failed
fail run raid1 array when we assemble array with the inactive disk only,
but the mdx_raid1 thread were not stop, Even if the associated resources
have been released. it will caused a NULL dereference when we do poweroff.
This causes the following Oops:
[ 287.587787] BUG: kernel NULL pointer dereference, address: 0000000000000070
[ 287.594762] #PF: supervisor read access in kernel mode
[ 287.599912] #PF: error_code(0x0000) - not-present page
[ 287.605061] PGD 0 P4D 0
[ 287.607612] Oops: 0000 [#1] SMP NOPTI
[ 287.611287] CPU: 3 PID: 5265 Comm: md0_raid1 Tainted: G U 5.10.146 #0
[ 287.619029]
Wiz
CVE-2023-54281 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54281 CVE-2023-54281 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54281 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: release path before inode lookup during the ino lookup ioctl
During the ino lookup ioctl we can end up calling btrfs_iget() to get an
inode reference while we are holding on a root's btree. If btrfs_iget()
needs to lookup the inode from the root's btree, because it's not
currently loaded in memory, then it will need to lock another or the
same path in the same root btree. This may result in a deadlock and
trigger the following lockdep splat:
## WARNING: possible circular locking dependency detected
6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Not tainted
syz-executor277/5012 is trying to acquire lock:
ffff88802df41710 (btrfs-tree-01){++++}-
Wiz
CVE-2025-68236 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68236 CVE-2025-68236 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68236 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: ufs: ufs-qcom: Fix UFS OCP issue during UFS power down (PC=3)
According to UFS specifications, the power-off sequence for a UFS device
includes:
Sending an SSU command with Power_Condition=3 and await a response.
Asserting RST_N low.
Turning off REF_CLK.
Turning off VCC.
Turning off VCCQ/VCCQ2.
As part of ufs shutdown, after the SSU command completion, asserting
hardware reset (HWRST) triggers the device firmware to wake up and
execute its reset routine. This routine initializes hardware blocks and
takes a few milliseconds to complete. During this time, the ICCQ draws a
large current.
This large ICCQ current may cause issues for the regul
Wiz
CVE-2026-23375 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23375 CVE-2026-23375 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23375 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm: thp: deny THP for files on anonymous inodes
file_thp_enabled() incorrectly allows THP for files on anonymous inodes
(e.g. guest_memfd and secretmem). These files are created via
alloc_file_pseudo(), which does not call get_write_access() and leaves
inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being
true, they appear as read-only regular files when
CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP
collapse.
Anonymous inodes can never pass the inode_is_open_for_write() check
since their i_writecount is never incremented through the normal VFS
open path. The right thing to do is to exclude them from THP eligibi
Wiz
CVE-2023-54086 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54086 CVE-2023-54086 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54086 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Add preempt_count_{sub,add} into btf id deny list
The recursion check in __bpf_prog_enter* and _ bpf_prog_exit*
leave preempt_count {sub,add} unprotected. When attaching trampoline to
them we get panic as follows,
[ 867.843050] BUG: TASK stack guard page was hit at 0000000009d325cf (stack is 0000000046a46a15..00000000537e7b28)
[ 867.843064] stack guard page: 0000 [#1] PREEMPT SMP NOPTI
[ 867.843067] CPU: 8 PID: 11009 Comm: trace Kdump: loaded Not tainted 6.2.0+ #4
[ 867.843100] Call Trace:
[ 867.843101] [ 867.843104] asm_exc_int3+0x3a/0x40
[ 867.843108] RIP: 0010:preempt_count_sub+0x1/0xa0
[ 867.843135] __bpf_prog_enter_recur+0x17/0x90
[ 867.8
Wiz
CVE-2023-54001 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54001 CVE-2023-54001 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54001 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: r8712: Fix memory leak in _r8712_init_xmit_priv()
In the above mentioned routine, memory is allocated in several places.
If the first succeeds and a later one fails, the routine will leak memory.
This patch fixes commit 2865d42c78a9 ("staging: r8712u: Add the new driver
to the mainline kernel"). A potential memory leak in
r8712_xmit_resource_alloc() is also addressed.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probabil
Wiz
CVE-2026-23070 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23070 [MEDIUM] CVE-2026-23070 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23070 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Octeontx2-af: Add proper checks for fwdata
firmware populates MAC address, link modes (supported, advertised)
and EEPROM data in shared firmware structure which kernel access
via MAC block(CGX/RPM).
Accessing fwdata, on boards booted with out MAC block leading to
kernel panics.
Internal error: Oops: 0000000096000005 [#1] SMP
[ 10.460721] Modules linked in:
[ 10.463779] CPU: 0 UID: 0 PID: 174 Comm: kworker/0:3 Not tainted 6.19.0-rc5-00154-g76ec646abdf7-dirty #3 PREEMPT
[ 10.474045] Hardware name: Marvell OcteonTX CN98XX board (DT)
[ 10.479793] Workqueue: events work_for_cpu_fn
[ 10.484159] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE
Wiz
CVE-2023-54032 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54032 CVE-2023-54032 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54032 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix race when deleting quota root from the dirty cow roots list
When disabling quotas we are deleting the quota root from the list
fs_info->dirty_cowonly_roots without taking the lock that protects it,
which is struct btrfs_fs_info::trans_lock. This unsynchronized list
manipulation may cause chaos if there's another concurrent manipulation
of this list, such as when adding a root to it with
ctree.c:add_root_to_dirty_list().
This can result in all sorts of weird failures caused by a race, such as
the following crash:
[337571.278245] general protection fault, probably for non-canonical address 0xdead000000000108: 0000 [#1] PREEMPT SMP PTI
[33
Wiz
CVE-2025-68345 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68345 CVE-2025-68345 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68345 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: hda: cs35l41: Fix NULL pointer dereference in cs35l41_hda_read_acpi()
The acpi_get_first_physical_node() function can return NULL, in which
case the get_device() function also returns NULL, but this value is
then dereferenced without checking,so add a check to prevent a crash.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5
Exploitation Probab
Wiz
CVE-2025-68354 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68354 CVE-2025-68354 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68354 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regulator: core: Protect regulator_supply_alias_list with regulator_list_mutex
regulator_supply_alias_list was accessed without any locking in
regulator_supply_alias(), regulator_register_supply_alias(), and
regulator_unregister_supply_alias(). Concurrent registration,
unregistration and lookups can race, leading to:
1 use-after-free if an alias entry is removed while being read,
2 duplicate entries when two threads register the same alias,
3 inconsistent alias mappings observed by consumers.
Protect all traversals, insertions and deletions on
regulator_supply_alias_list with the existing regulator_list_mutex.
Source : NVD
## 5.5
Score
Publi
Wiz
CVE-2025-68823 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68823 [MEDIUM] CVE-2025-68823 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68823 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ublk: fix deadlock when reading partition table
When one process(such as udev) opens ublk block device (e.g., to read
the partition table via bdev_open()), a deadlock[1] can occur:
bdev_open() grabs disk->open_mutex
The process issues read I/O to ublk backend to read partition table
In __ublk_complete_rq(), blk_update_request() or blk_mq_end_request() runs bio->bi_end_io() callbacks
If this triggers fput() on file descriptor of ublk block device, the work may be deferred to current task's task work (see fput() implementation)
This eventually calls blkdev_release() from the same context
blkdev_release() tries to grab disk->open_mutex again
Dea
Wiz
CVE-2023-54150 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54150 CVE-2023-54150 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54150 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amd: Fix an out of bounds error in BIOS parser
The array is hardcoded to 8 in atomfirmware.h, but firmware provides
a bigger one sometimes. Deferencing the larger array causes an out
of bounds error.
commit 4fc1ba4aa589 ("drm/amd/display: fix array index out of bound error
in bios parser") fixed some of this, but there are two other cases
not covered by it. Fix those as well.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Prob
Wiz
CVE-2022-50875 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50875 CVE-2022-50875 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50875 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
of: overlay: fix null pointer dereferencing in find_dup_cset_node_entry() and find_dup_cset_prop()
When kmalloc() fail to allocate memory in kasprintf(), fn_1 or fn_2 will
be NULL, and strcmp() will cause null pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-devel
kernel-zfcpdump-modules-internal
Sources
NVD
Debian 11, 12, 13, 14 Has Fix
Wiz
CVE-2026-23049 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23049 CVE-2026-23049 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23049 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/panel-simple: fix connector type for DataImage SCF0700C48GGU18 panel
The connector type for the DataImage SCF0700C48GGU18 panel is missing and
devm_drm_panel_bridge_add() requires connector type to be set. This leads
to a warning and a backtrace in the kernel log and panel does not work:
"
WARNING: CPU: 3 PID: 38 at drivers/gpu/drm/bridge/panel.c:379 devm_drm_of_get_bridge+0xac/0xb8
"
The warning is triggered by a check for valid connector type in
devm_drm_panel_bridge_add(). If there is no valid connector type
set for a panel, the warning is printed and panel is not added.
Fill in the missing connector type to fix the warning and make
the panel
Wiz
CVE-2022-50782 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50782 CVE-2022-50782 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50782 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix bug_on in __es_tree_search caused by bad quota inode
## We got a issue as fllows:
kernel BUG at fs/ext4/extents_status.c:202!
invalid opcode: 0000 [#1] PREEMPT SMP
CPU: 1 PID: 810 Comm: mount Not tainted 6.1.0-rc1-next-g9631525255e3 #352
RIP: 0010:__es_tree_search.isra.0+0xb8/0xe0
RSP: 0018:ffffc90001227900 EFLAGS: 00010202
RAX: 0000000000000000 RBX: 0000000077512a0f RCX: 0000000000000000
RDX: 0000000000000002 RSI: 0000000000002a10 RDI: ffff8881004cd0c8
RBP: ffff888177512ac8 R08: 47ffffffffffffff R09: 0000000000000001
R10: 0000000000000001 R11: 00000000000679af R12: 0000000000002a10
R13: ffff888177512d88 R14: 0000000077512a10 R15: 00000
Wiz
CVE-2025-68197 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68197 CVE-2025-68197 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68197 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: Fix null pointer dereference in bnxt_bs_trace_check_wrap()
With older FW, we may get the ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER
for FW trace data type that has not been initialized. This will result
in a crash in bnxt_bs_trace_type_wrap(). Add a guard to check for a
valid magic_byte pointer before proceeding.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-
Wiz
CVE-2023-54079 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54079 CVE-2023-54079 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54079 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
power: supply: bq27xxx: Fix poll_interval handling and races on remove
Before this patch bq27xxx_battery_teardown() was setting poll_interval = 0
to avoid bq27xxx_battery_update() requeuing the delayed_work item.
There are 2 problems with this:
If the driver is unbound through sysfs, rather then the module being
rmmod-ed, this changes poll_interval unexpectedly
This is racy, after it being set poll_interval could be changed
before bq27xxx_battery_update() checks it through
/sys/module/bq27xxx_battery/parameters/poll_interval
Fix this by added a removed attribute to struct bq27xxx_device_info and
using that instead of setting poll_interval to 0.
Wiz
CVE-2026-23212 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23212 [MEDIUM] CVE-2026-23212 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23212 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bonding: annotate data-races around slave->last_rx
slave->last_rx and slave->target_last_arp_rx[...] can be read and written
locklessly. Add READ_ONCE() and WRITE_ONCE() annotations.
syzbot reported:
BUG: KCSAN: data-race in bond_rcv_validate / bond_rcv_validate
write to 0xffff888149f0d428 of 8 bytes by interrupt on cpu 1:
bond_rcv_validate+0x202/0x7a0 drivers/net/bonding/bond_main.c:3335
bond_handle_frame+0xde/0x5e0 drivers/net/bonding/bond_main.c:1533
__netif_receive_skb_core+0x5b1/0x1950 net/core/dev.c:6039
__netif_receive_skb_one_core net/core/dev.c:6150 [inline]
__netif_receive_skb+0x59/0x270 net/core/dev.c:6265
netif_receive_skb_internal ne
Wiz
CVE-2023-54168 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54168 CVE-2023-54168 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54168 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/mlx4: Prevent shift wrapping in set_user_sq_size()
The ucmd->log_sq_bb_count variable is controlled by the user so this
shift can wrap. Fix it by using check_shl_overflow() in the same way
that it was done in commit 515f60004ed9 ("RDMA/hns: Prevent undefined
behavior in hns_roce_set_user_sq_size()").
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt
linux-aws-5.
Wiz
CVE-2026-23182 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23182 CVE-2026-23182 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23182 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: tegra: Fix a memory leak in tegra_slink_probe()
In tegra_slink_probe(), when platform_get_irq() fails, it directly
returns from the function with an error code, which causes a memory leak.
Replace it with a goto label to ensure proper cleanup.
Source : NVD
Published February 14, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 18.9
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-uek64k
linux-oracle
Sources
NVD
Debian 11 Has Fix Added at: Mar 13, 2
Wiz
CVE-2026-22977 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22977 [MEDIUM] CVE-2026-22977 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22977 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: sock: fix hardened usercopy panic in sock_recv_errqueue
skbuff_fclone_cache was created without defining a usercopy region,
[1] unlike skbuff_head_cache which properly whitelists the cb[] field.
[2] This causes a usercopy BUG() when CONFIG_HARDENED_USERCOPY is
enabled and the kernel attempts to copy sk_buff.cb data to userspace
via sock_recv_errqueue() -> put_cmsg().
The crash occurs when: 1. TCP allocates an skb using alloc_skb_fclone()
(from skbuff_fclone_cache) [1]
2. The skb is cloned via skb_clone() using the pre-allocated fclone
[3] 3. The cloned skb is queued to sk_error_queue for timestamp
reporting 4. Userspace reads the error queue v
Wiz
CVE-2026-23089 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23089 [HIGH] CVE-2026-23089 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23089 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: usb-audio: Fix use-after-free in snd_usb_mixer_free()
When snd_usb_create_mixer() fails, snd_usb_mixer_free() frees
mixer->id_elems but the controls already added to the card still
reference the freed memory. Later when snd_card_register() runs,
the OSS mixer layer calls their callbacks and hits a use-after-free read.
Call trace:
get_ctl_value+0x63f/0x820 sound/usb/mixer.c:411
get_min_max_with_quirks.isra.0+0x240/0x1f40 sound/usb/mixer.c:1241
mixer_ctl_feature_info+0x26b/0x490 sound/usb/mixer.c:1381
snd_mixer_oss_build_test+0x174/0x3a0 sound/core/oss/mixer_oss.c:887
...
snd_card_register+0x4ed/0x6d0 sound/core/init.c:923
usb_audio_probe+0x5ef
Wiz
CVE-2025-71223 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71223 [MEDIUM] CVE-2025-71223 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71223 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb/server: fix refcount leak in smb2_open()
When ksmbd_vfs_getattr() fails, the reference count of ksmbd_file
must be released.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-nvidia-tegra-igx
linux-riscv-6.17
Sources
NVD
Debian 11, 12 No Fix Added at: Feb 15, 2026
Debian 13, 14 Severity MEDIUM Has Fix Added at: Feb 15, 2026
Echo Se
Wiz
CVE-2026-23233 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23233 [HIGH] CVE-2026-23233 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23233 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
f2fs: fix to avoid mapping wrong physical block for swapfile
Xiaolong Guo reported a f2fs bug in bugzilla [1]
[1] https://bugzilla.kernel.org/show_bug.cgi?id=220951
Quoted:
"When using stress-ng's swap stress test on F2FS filesystem with kernel 6.6+,
the system experiences data corruption leading to either:
1 dm-verity corruption errors and device reboot
2 F2FS node corruption errors and boot hangs
The issue occurs specifically when:
1 Using F2FS filesystem (ext4 is unaffected)
2 Swapfile size is less than F2FS section size (2MB)
3 Swapfile has fragmented physical layout (multiple non-contiguous extents)
4 Kernel version is 6.6+ (6.1 is unaffect
Wiz
CVE-2023-54177 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54177 CVE-2023-54177 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54177 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
quota: fix warning in dqgrab()
There's issue as follows when do fault injection:
WARNING: CPU: 1 PID: 14870 at include/linux/quotaops.h:51 dquot_disable+0x13b7/0x18c0
Modules linked in:
CPU: 1 PID: 14870 Comm: fsconfig Not tainted 6.3.0-next-20230505-00006-g5107a9c821af-dirty #541
RIP: 0010:dquot_disable+0x13b7/0x18c0
RSP: 0018:ffffc9000acc79e0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88825e41b980
RDX: 0000000000000000 RSI: ffff88825e41b980 RDI: 0000000000000002
RBP: ffff888179f68000 R08: ffffffff82087ca7 R09: 0000000000000000
R10: 0000000000000001 R11: ffffed102f3ed026 R12: ffff888179f68130
R13: ffff888179f68110 R14: df
Wiz
CVE-2022-50771 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50771 CVE-2022-50771 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50771 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rcu: Fix __this_cpu_read() lockdep warning in rcu_force_quiescent_state()
Running rcutorture with non-zero fqs_duration module parameter in a
kernel built with CONFIG_PREEMPTION=y results in the following splat:
BUG: using __this_cpu_read() in preemptible [00000000]
code: rcu_torture_fqs/398
caller is __this_cpu_preempt_check+0x13/0x20
CPU: 3 PID: 398 Comm: rcu_torture_fqs Not tainted 6.0.0-rc1-yoctodev-standard+
Call Trace: dump_stack_lvl+0x5b/0x86
dump_stack+0x10/0x16
check_preemption_disabled+0xe5/0xf0
__this_cpu_preempt_check+0x13/0x20
rcu_force_quiescent_state.part.0+0x1c/0x170
rcu_force_quiescent_state+0x1e/0x30
rcu_torture_fqs+0xca/0x160
? r
Wiz
CVE-2025-71151 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71151 [MEDIUM] CVE-2025-71151 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71151 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: Fix memory and information leak in smb3_reconfigure()
In smb3_reconfigure(), if smb3_sync_session_ctx_passwords() fails, the
function returns immediately without freeing and erasing the newly
allocated new_password and new_password2. This causes both a memory leak
and a potential information leak.
Fix this by calling kfree_sensitive() on both password buffers before
returning in this error case.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitati
Wiz
CVE-2026-23150 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23150 [MEDIUM] CVE-2026-23150 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23150 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfc: llcp: Fix memleak in nfc_llcp_send_ui_frame().
syzbot reported various memory leaks related to NFC, struct
nfc_llcp_sock, sk_buff, nfc_dev, etc. 0
The leading log hinted that nfc_llcp_send_ui_frame() failed
to allocate skb due to sock_error(sk) being -ENXIO.
ENXIO is set by nfc_llcp_socket_release() when struct
nfc_llcp_local is destroyed by local_cleanup().
The problem is that there is no synchronisation between
nfc_llcp_send_ui_frame() and local_cleanup(), and skb
could be put into local->tx_queue after it was purged in
local_cleanup():
CPU1 CPU2
nfc_llcp_send_ui_frame() local_cleanup()
|- do { '
|- pdu = nfc_alloc_send_skb(..., &err)
|
Wiz
CVE-2022-50723 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50723 CVE-2022-50723 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50723 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: fix memory leak in bnxt_nvm_test()
Free the kzalloc'ed buffer before returning in the success path.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-abi-stablelists
kernel-core
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8 Severity MEDIUM Has Fix Added at: Dec 26, 2025
Red Hat 9 Severity MEDIUM
Wiz
CVE-2025-68311 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68311 CVE-2025-68311 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68311 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tty: serial: ip22zilog: Use platform device for probing
After commit 84a9582fd203 ("serial: core: Start managing serial controllers
to enable runtime PM") serial drivers need to provide a device in
struct uart_port.dev otherwise an oops happens. To fix this issue
for ip22zilog driver switch driver to a platform driver and setup
the serial device in sgi-ip22 code.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exp
Wiz
CVE-2023-54137 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54137 CVE-2023-54137 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54137 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vfio/type1: fix cap_migration information leak
Fix an information leak where an uninitialized hole in struct
vfio_iommu_type1_info_cap_migration on the stack is exposed to userspace.
The definition of struct vfio_iommu_type1_info_cap_migration contains a hole as
shown in this pahole(1) output:
struct vfio_iommu_type1_info_cap_migration {
struct vfio_info_cap_header header; /* 0 8 /
__u32 flags; / 8 4 */
/* XXX 4 bytes hole, try to pack */
__u64 pgsize_bitmap; /* 16 8 */
__u64 max_dirty_bitmap_size; /* 24 8 */
/* size: 32, cachelines: 1, members: 4 */
/* sum members: 28, holes: 1, sum holes: 4 */
/* last cacheline: 32 bytes */
};
The cap_mig v
Wiz
CVE-2026-22989 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22989 [MEDIUM] CVE-2026-22989 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22989 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: check that server is running in unlock_filesystem
If we are trying to unlock the filesystem via an administrative
interface and nfsd isn't running, it crashes the server. This
happens currently because nfsd4_revoke_states() access state
structures (eg., conf_id_hashtbl) that has been freed as a part
of the server shutdown.
[ 59.465072] Call trace:
[ 59.465308] nfsd4_revoke_states+0x1b4/0x898 [nfsd] (P)
[ 59.465830] write_unlock_fs+0x258/0x440 [nfsd]
[ 59.466278] nfsctl_transaction_write+0xb0/0x120 [nfsd]
[ 59.466780] vfs_write+0x1f0/0x938
[ 59.467088] ksys_write+0xfc/0x1f8
[ 59.467395] __arm64_sys_write+0x74/0xb8
[ 59.467746] invoke_syscall.c
Wiz
CVE-2022-50733 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50733 CVE-2022-50733 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50733 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: idmouse: fix an uninit-value in idmouse_open
In idmouse_create_image, if any ftip_command fails, it will
go to the reset label. However, this leads to the data in
bulk_in_buffer[HEADER..IMGSIZE] uninitialized. And the check
for valid image incurs an uninitialized dereference.
Fix this by moving the check before reset label since this
check only be valid if the data after bulk_in_buffer[HEADER]
has concrete data.
Note that this is found by KMSAN, so only kernel compilation
is tested.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA
Wiz
CVE-2025-68340 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68340 [MEDIUM] CVE-2025-68340 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68340 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
team: Move team device type change at the end of team_port_add
Attempting to add a port device that is already up will expectedly fail,
but not before modifying the team device header_ops.
In the case of the syzbot reproducer the gre0 device is
already in state UP when it attempts to add it as a
port device of team0, this fails but before that
header_ops->create of team0 is changed from eth_header to ipgre_header
in the call to team_dev_type_check_change.
Later when we end up in ipgre_header() struct ip_tunnel* points to nonsense
as the private data of the device still holds a struct team.
Example sequence of iproute2 commands to reproduce the ha
Wiz
CVE-2025-68762 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68762 CVE-2025-68762 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68762 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: netpoll: initialize work queue before error checks
Prevent a kernel warning when netconsole setup fails on devices with
IFF_DISABLE_NETPOLL flag. The warning (at kernel/workqueue.c:4242 in
__flush_work) occurs because the cleanup path tries to cancel an
uninitialized work queue.
When __netpoll_setup() encounters a device with IFF_DISABLE_NETPOLL,
it fails early and calls skb_pool_flush() for cleanup. This function
calls cancel_work_sync(&np->refill_wq), but refill_wq hasn't been
initialized yet, triggering the warning.
Move INIT_WORK() to the beginning of __netpoll_setup(), ensuring the
work queue is properly initialized before any potential
Wiz
CVE-2023-54181 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54181 CVE-2023-54181 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54181 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix issue in verifying allow_ptr_leaks
After we converted the capabilities of our networking-bpf program from
cap_sys_admin to cap_net_admin+cap_bpf, our networking-bpf program
failed to start. Because it failed the bpf verifier, and the error log
is "R3 pointer comparison prohibited".
A simple reproducer as follows,
SEC("cls-ingress")
int ingress(struct __sk_buff *skb)
{
struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr);
if ((long)(iph + 1) > (long)skb->data_end)
return TC_ACT_STOLEN;
return TC_ACT_OK;
}
Per discussion with Yonghong and Alexei [1], comparison of two packet
pointers is not a pointer leak. This patch fixes
Wiz
CVE-2023-53823 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53823 CVE-2023-53823 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53823 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block/rq_qos: protect rq_qos apis with a new lock
commit 50e34d78815e ("block: disable the elevator int del_gendisk")
move rq_qos_exit() from disk_release() to del_gendisk(), this will
introduce some problems:
If rq_qos_add() is triggered by enabling iocost/iolatency through
cgroupfs, then it can concurrent with del_gendisk(), it's not safe to
write 'q->rq_qos' concurrently.
Activate cgroup policy that is relied on rq_qos will call
rq_qos_add() and blkcg_activate_policy(), and if rq_qos_exit() is
called in the middle, null-ptr-dereference will be triggered in
blkcg_activate_policy().
blkg_conf_open_bdev() can call blkdev_get_no_open() first to fi
Wiz
CVE-2026-23097 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23097 [MEDIUM] CVE-2026-23097 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23097 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
migrate: correct lock ordering for hugetlb file folios
Syzbot has found a deadlock (analyzed by Lance Yang):
Task (5749): Holds folio_lock, then tries to acquire i_mmap_rwsem(read lock).
Task (5754): Holds i_mmap_rwsem(write lock), then tries to acquirefolio_lock.
migrate_pages()
-> migrate_hugetlbs()
-> unmap_and_move_huge_page() remove_migration_ptes()
-> __rmap_walk_file()
-> i_mmap_lock_read() hugetlbfs_punch_hole() hugetlbfs_zero_partial_page()
-> filemap_lock_hugetlb_folio()
-> filemap_lock_folio()
-> __filemap_get_folio <- Waits for folio_lock!
The migration path is the one taking locks in the wrong order according to
the documentation at
Wiz
CVE-2025-40350 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40350 CVE-2025-40350 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40350 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for striding RQ
XDP programs can change the layout of an xdp_buff through
bpf_xdp_adjust_tail() and bpf_xdp_adjust_head(). Therefore, the driver
cannot assume the size of the linear data area nor fragments. Fix the
bug in mlx5 by generating skb according to xdp_buff after XDP programs
run.
Currently, when handling multi-buf XDP, the mlx5 driver assumes the
layout of an xdp_buff to be unchanged. That is, the linear data area
continues to be empty and fragments remain the same. This may cause
the driver to generate erroneous skb or triggering a kernel
warning. When an XDP program added linear
Wiz
CVE-2023-53834 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53834 CVE-2023-53834 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53834 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iio: adc: ina2xx: avoid NULL pointer dereference on OF device match
The affected lines were resulting in a NULL pointer dereference on our
platform because the device tree contained the following list of
compatible strings:
power-sensor@40 {
compatible = "ti,ina232", "ti,ina231";
...
};
Since the driver doesn't declare a compatible string "ti,ina232", the OF
matching succeeds on "ti,ina231". But the I2C device ID info is
populated via the first compatible string, cf. modalias population in
of_i2c_get_board_info(). Since there is no "ina232" entry in the legacy
I2C device ID table either, the struct i2c_device_id *id pointer in the
probe function i
Wiz
CVE-2023-53850 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53850 CVE-2023-53850 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53850 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iavf: use internal state to free traffic IRQs
If the system tries to close the netdev while iavf_reset_task() is
running, __LINK_STATE_START will be cleared and netif_running() will
return false in iavf_reinit_interrupt_scheme(). This will result in
iavf_free_traffic_irqs() not being called and a leak as follows:
[7632.489326] remove_proc_entry: removing non-empty directory 'irq/999', leaking at least 'iavf-enp24s0f0v0-TxRx-0'
[7632.490214] WARNING: CPU: 0 PID: 10 at fs/proc/generic.c:718 remove_proc_entry+0x19b/0x1b0
is shown when pci_disable_msix() is later called. Fix by using the
internal adapter state. The traffic IRQs will always exist if
st
Wiz
CVE-2023-54305 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54305 CVE-2023-54305 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54305 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: refuse to create ea block when umounted
The ea block expansion need to access s_root while it is
already set as NULL when umount is triggered. Refuse this
request to avoid panic.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-kdump
libperf-devel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6,
Wiz
CVE-2023-54087 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54087 CVE-2023-54087 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54087 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ubi: Fix possible null-ptr-deref in ubi_free_volume()
It willl cause null-ptr-deref in the following case:
uif_init()
ubi_add_volume()
cdev_add() -> if it fails, call kill_volumes()
device_register()
kill_volumes() -> if ubi_add_volume() fails call this function
ubi_free_volume()
cdev_del()
device_unregister() -> trying to delete a not added device,
it causes null-ptr-deref
So in ubi_free_volume(), it delete devices whether they are added
or not, it will causes null-ptr-deref.
Handle the error case whlie calling ubi_add_volume() to fix this
problem. If add volume fails, set the corresponding vol to null,
so it can not be accessed in kill_volumes
Wiz
CVE-2026-23196 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23196 [MEDIUM] CVE-2026-23196 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23196 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: Intel-thc-hid: Intel-thc: Add safety check for reading DMA buffer
Add DMA buffer readiness check before reading DMA buffer to avoid
unexpected NULL pointer accessing.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-core
kernel-64k-debug-core
Sources
NVD
Debian 11, 12, 13 No Fix Added at: Feb 15, 2026
Debian 14 Severity M
Wiz
CVE-2026-23302 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23302 CVE-2026-23302 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23302 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: annotate data-races around sk->sk_{data_ready,write_space}
skmsg (and probably other layers) are changing these pointers
while other cpus might read them concurrently.
Add corresponding READ_ONCE()/WRITE_ONCE() annotations
for UDP, TCP and AF_UNIX.
Source : NVD
## 6.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules-core
kernel-rt-64k-debu
Wiz
CVE-2026-31392 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31392 CVE-2026-31392 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31392 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix krb5 mount with username option
Customer reported that some of their krb5 mounts were failing against
a single server as the client was trying to mount the shares with
wrong credentials. It turned out the client was reusing SMB session
from first mount to try mounting the other shares, even though a
different username= option had been specified to the other mounts.
By using username mount option along with sec=krb5 to search for
principals from keytab is supported by cifs.upcall(8) since
cifs-utils-4.8. So fix this by matching username mount option in
match_session() even with Kerberos.
For example, the second mount below should f
Wiz
CVE-2023-54291 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54291 CVE-2023-54291 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54291 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vduse: fix NULL pointer dereference
vduse_vdpa_set_vq_affinity callback can be called
with NULL value as cpu_mask when deleting the vduse
device.
This patch resets virtqueue's IRQ affinity mask value
to set all CPUs instead of dereferencing NULL cpu_mask.
[ 4760.952149] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 4760.959110] #PF: supervisor read access in kernel mode
[ 4760.964247] #PF: error_code(0x0000) - not-present page
[ 4760.969385] PGD 0 P4D 0
[ 4760.971927] Oops: 0000 [#1] PREEMPT SMP PTI
[ 4760.976112] CPU: 13 PID: 2346 Comm: vdpa Not tainted 6.4.0-rc6+ #4
[ 4760.982291] Hardware name: Dell Inc. PowerEdge R640/0W23H
Wiz
CVE-2022-50756 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50756 CVE-2022-50756 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50756 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-pci: fix mempool alloc size
Convert the max size to bytes to match the units of the divisor that
calculates the worst-case number of PRP entries.
The result is used to determine how many PRP Lists are required. The
code was previously rounding this to 1 list, but we can require 2 in the
worst case. In that scenario, the driver would corrupt memory beyond the
size provided by the mempool.
While unlikely to occur (you'd need a 4MB in exactly 127 phys segments
on a queue that doesn't support SGLs), this memory corruption has been
observed by kfence.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
L
Wiz
CVE-2025-71186 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71186 [MEDIUM] CVE-2025-71186 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71186 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: stm32: dmamux: fix device leak on route allocation
Make sure to drop the reference taken when looking up the DMA mux
platform device during route allocation.
Note that holding a reference to a device does not prevent its driver
data from going away so there is no point in keeping the reference.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.5
Exploitation Probability (EPSS) N/A
Affected packages and li
Wiz
CVE-2026-23391 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23391 [HIGH] CVE-2026-23391 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23391 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: xt_CT: drop pending enqueued packets on template removal
Templates refer to objects that can go away while packets are sitting in
nfqueue refer to:
helper, this can be an issue on module removal.
timeout policy, nfnetlink_cttimeout might remove it.
The use of templates with zone and event cache filter are safe, since
this just copies values.
Flush these enqueued packets in case the template rule gets removed.
Source : NVD
## 7.8
Score
Published March 25, 2026
Severity HIGH
CNA Score 7.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Dat
Wiz
CVE-2026-33191 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.7
CVE-2026-33191 [HIGH] CVE-2026-33191 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-33191 :
Linux Ubuntu vulnerability analysis and mitigation
Free5GC is an open-source Linux Foundation project for 5th generation (5G) mobile core networks. Versions prior to 1.4.2
are vulnerable to null byte injection in URL path parameters. A remote attacker can inject null bytes (URL-encoded as %00) into the supi path parameter of the UDM's Nudm_SubscriberDataManagement API. This causes URL parsing failure in Go's net/url package with the error "invalid control character in URL", resulting in a 500 Internal Server Error. This null byte injection vulnerability can be exploited for denial of service attacks. When the supi parameter contains null characters, the UDM attempts to construct a URL for UDR that includes these control characters. Go's URL parser rejects them, causin
Wiz
CVE-2025-68356 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68356 CVE-2025-68356 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68356 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gfs2: Prevent recursive memory reclaim
Function new_inode() returns a new inode with inode->i_mapping->gfp_mask
set to GFP_HIGHUSER_MOVABLE. This value includes the __GFP_FS flag, so
allocations in that address space can recurse into filesystem memory
reclaim. We don't want that to happen because it can consume a
significant amount of stack memory.
Worse than that is that it can also deadlock: for example, in several
places, gfs2_unstuff_dinode() is called inside filesystem transactions.
This calls filemap_grab_folio(), which can allocate a new folio, which
can trigger memory reclaim. If memory reclaim recurses into the
filesystem and starts anothe
Wiz
CVE-2023-53820 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53820 CVE-2023-53820 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53820 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
loop: loop_set_status_from_info() check before assignment
In loop_set_status_from_info(), lo->lo_offset and lo->lo_sizelimit should
be checked before reassignment, because if an overflow error occurs, the
original correct value will be changed to the wrong value, and it will not
be changed back.
More, the original patch did not solve the problem, the value was set and
ioctl returned an error, but the subsequent io used the value in the loop
driver, which still caused an alarm:
loop_handle_cmd
do_req_filebacked
loff_t pos = ((loff_t) blk_rq_pos(rq) lo_offset;
lo_rw_aio
cmd->iocb.ki_pos = pos
Source : NVD
Published December 9, 2025
CNA Score N/A
Wiz
CVE-2026-23395 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.8
CVE-2026-23395 [HIGH] CVE-2026-23395 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23395 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ
Currently the code attempts to accept requests regardless of the
command identifier which may cause multiple requests to be marked
as pending (FLAG_DEFER_SETUP) which can cause more than
L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer
causing an overflow.
The spec is quite clear that the same identifier shall not be used on
subsequent requests:
'Within each signaling channel a different Identifier shall be used
for each successive request or indication.' https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-ada
Wiz
CVE-2023-53826 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53826 CVE-2023-53826 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53826 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ubi: Fix UAF wear-leveling entry in eraseblk_count_seq_show()
Wear-leveling entry could be freed in error path, which may be accessed
again in eraseblk_count_seq_show(), for example:
__erase_worker eraseblk_count_seq_show
wl = ubi->lookuptbl[*block_number]
if (wl)
wl_entry_destroy
ubi->lookuptbl[e->pnum] = NULL
kmem_cache_free(ubi_wl_entry_slab, e)
erase_count = wl->ec // UAF!
Wear-leveling entry updating/accessing in ubi->lookuptbl should be
protected by ubi->wl_lock, fix it by adding ubi->wl_lock to serialize
wl entry accessing between wl_entry_destroy() and
eraseblk_count_seq_show().
Fetch a reproducer in [Link].
Source : NVD
Published Decem
Wiz
CVE-2026-23213 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23213 [MEDIUM] CVE-2026-23213 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23213 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amd/pm: Disable MMIO access during SMU Mode 1 reset
During Mode 1 reset, the ASIC undergoes a reset cycle and becomes
temporarily inaccessible via PCIe. Any attempt to access MMIO registers
during this window (e.g., from interrupt handlers or other driver threads)
can result in uncompleted PCIe transactions, leading to NMI panics or
system hangs.
no_hw_access
smp_mb()
(cherry picked from commit 7edb503fe4b6d67f47d8bb0dfafb8e699bb0f8a4)
Source : NVD
## 5.5
Score
Published February 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release D
Wiz
CVE-2023-54194 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54194 CVE-2023-54194 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54194 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
exfat: use kvmalloc_array/kvfree instead of kmalloc_array/kfree
The call stack shown below is a scenario in the Linux 4.19 kernel.
Allocating memory failed where exfat fs use kmalloc_array due to
system memory fragmentation, while the u-disk was inserted without
recognition.
Devices such as u-disk using the exfat file system are pluggable and
may be insert into the system at any time.
However, long-term running systems cannot guarantee the continuity of
physical memory. Therefore, it's necessary to address this issue.
Binder:2632_6: page allocation failure: order:4,
mode:0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null)
Call trace:
[242178.097582] d
Wiz
CVE-2022-50856 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50856 CVE-2022-50856 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50856 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: Fix xid leak in cifs_ses_add_channel()
Before return, should free the xid, otherwise, the
xid will be leaked.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-tools
perf
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6 Severity LOW No Fix Added at: Dec 31, 2025
Red Hat 8 Severity LOW Has Fix Added
Wiz
CVE-2026-31402 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31402 CVE-2026-31402 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31402 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: fix heap overflow in NFSv4.0 LOCK replay cache
The NFSv4.0 replay cache uses a fixed 112-byte inline buffer
(rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses.
This size was calculated based on OPEN responses and does not account
for LOCK denied responses, which include the conflicting lock owner as
a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT).
When a LOCK operation is denied due to a conflict with an existing lock
that has a large owner, nfsd4_encode_operation() copies the full encoded
response into the undersized replay buffer via read_bytes_from_xdr_buf()
with no bounds check. This results in a slab-out-of-b
Wiz
CVE-2023-54111 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54111 CVE-2023-54111 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54111 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pinctrl: rockchip: Fix refcount leak in rockchip_pinctrl_parse_groups
of_find_node_by_phandle() returns a node pointer with refcount incremented,
We should use of_node_put() on it when not needed anymore.
Add missing of_node_put() to avoid refcount leak.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
gfs2-kmp-default
kernel-default-devel
Sources
NVD
Debian 11, 12, 13, 14
Wiz
CVE-2026-23052 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23052 CVE-2026-23052 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23052 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ftrace: Do not over-allocate ftrace memory
The pg_remaining calculation in ftrace_process_locs() assumes that
ENTRIES_PER_PAGE multiplied by 2^order equals the actual capacity of the
allocated page group. However, ENTRIES_PER_PAGE is PAGE_SIZE / ENTRY_SIZE
(integer division). When PAGE_SIZE is not a multiple of ENTRY_SIZE (e.g.
4096 / 24 = 170 with remainder 16), high-order allocations (like 256 pages)
have significantly more capacity than 256 * 170. This leads to pg_remaining
being underestimated, which in turn makes skip (derived from skipped -
pg_remaining) larger than expected, causing the WARN(skip != remaining)
to trigger.
Extra allocated pag
Wiz
CVE-2026-23091 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23091 [MEDIUM] CVE-2026-23091 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23091 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
intel_th: fix device leak on output open()
Make sure to drop the reference taken when looking up the th device
during output device open() on errors and on close().
Note that a recent commit fixed the leak in a couple of open() error
paths but not all of them, and the reference is still leaking on
successful open().
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected pack
Wiz
CVE-2025-68305 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68305 CVE-2025-68305 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68305 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_sock: Prevent race in socket write iter and sock bind
There is a potential race condition between sock bind and socket write
iter. bind may free the same cmd via mgmt_pending before write iter sends
the cmd, just as syzbot reported in UAF[1].
Here we use hci_dev_lock to synchronize the two, thereby avoiding the
UAF mentioned in [1].
[1]
syzbot reported:
BUG: KASAN: slab-use-after-free in mgmt_pending_remove+0x3b/0x210 net/bluetooth/mgmt_util.c:316
Read of size 8 at addr ffff888077164818 by task syz.0.17/5989
Call Trace:
mgmt_pending_remove+0x3b/0x210 net/bluetooth/mgmt_util.c:316
set_link_security+0x5c2/0x710 net/bluetooth/mgmt.c:19
Wiz
CVE-2026-23357 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23357 CVE-2026-23357 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23357 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: mcp251x: fix deadlock in error path of mcp251x_open
The mcp251x_open() function call free_irq() in its error path with the
mpc_lock mutex held. But if an interrupt already occurred the
interrupt handler will be waiting for the mpc_lock and free_irq() will
deadlock waiting for the handler to finish.
This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can:
mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but
for the error path.
priv->force_quit = 1
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CI
Wiz
CVE-2026-23228 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23228 [MEDIUM] CVE-2026-23228 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23228 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: server: fix leak of active_num_conn in ksmbd_tcp_new_connection()
On kthread_run() failure in ksmbd_tcp_new_connection(), the transport is
freed via free_transport(), which does not decrement active_num_conn,
leaking this counter.
Replace free_transport() with ksmbd_tcp_disconnect().
Source : NVD
## 5.5
Score
Published February 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel
Wiz
CVE-2023-54024 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54024 CVE-2023-54024 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54024 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: Destroy target device if coalesced MMIO unregistration fails
Destroy and free the target coalesced MMIO device if unregistering said
device fails. As clearly noted in the code, kvm_io_bus_unregister_dev()
does not destroy the target device.
BUG: memory leak
unreferenced object 0xffff888112a54880 (size 64):
comm "syz-executor.2", pid 5258, jiffies 4297861402 (age 14.129s)
hex dump (first 32 bytes):
38 c7 67 15 00 c9 ff ff 38 c7 67 15 00 c9 ff ff 8.g.....8.g.....
e0 c7 e1 83 ff ff ff ff 00 30 67 15 00 c9 ff ff .........0g.....
backtrace:
[] kmalloc include/linux/slab.h:556 [inline]
[] kzalloc include/linux/slab.h:690 [inline]
[] kvm_vm_ioctl_reg
Wiz
CVE-2023-54285 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2023-54285 [HIGH] CVE-2023-54285 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54285 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iomap: Fix possible overflow condition in iomap_write_delalloc_scan
folio_next_index() returns an unsigned long value which left shifted
by PAGE_SHIFT could possibly cause an overflow on 32-bit system. Instead
use folio_pos(folio) + folio_size(folio), which does this correctly.
Source : NVD
## 7.8
Score
Published December 30, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 1.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-ibm
kernel-rt
Wiz
CVE-2025-68174 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68174 CVE-2025-68174 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68174 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
amd/amdkfd: enhance kfd process check in switch partition
current switch partition only check if kfd_processes_table is empty.
kfd_prcesses_table entry is deleted in kfd_process_notifier_release, but
kfd_process tear down is in kfd_process_wq_release.
consider two processes:
Process A (workqueue) -> kfd_process_wq_release -> Access kfd_node member
Process B switch partition -> amdgpu_xcp_pre_partition_switch -> amdgpu_amdkfd_device_fini_sw
-> kfd_node tear down.
Process A and B may trigger a race as shown in dmesg log.
This patch is to resolve the race by adding an atomic kfd_process counter
kfd_processes_count, it increment as create kfd proces
Wiz
CVE-2026-23003 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23003 [MEDIUM] CVE-2026-23003 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23003 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ip6_tunnel: use skb_vlan_inet_prepare() in __ip6_tnl_rcv()
Blamed commit did not take care of VLAN encapsulations
as spotted by syzbot [1].
Use skb_vlan_inet_prepare() instead of pskb_inet_may_pull().
[1]
BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline]
BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline]
BUG: KMSAN: uninit-value in IP6_ECN_decapsulate+0x7a8/0x1fa0 include/net/inet_ecn.h:321
__INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline]
INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline]
IP6_ECN_decapsulate+0x7a8/0x1fa0 include/net/inet_ecn.h:321
ip6ip6_dscp_ec
Wiz
CVE-2025-71160 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71160 [MEDIUM] CVE-2025-71160 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71160 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: avoid chain re-validation if possible
Hamza Mahfooz reports cpu soft lock-ups in
nft_chain_validate():
watchdog: BUG: soft lockup - CPU#1 stuck for 27s! [iptables-nft-re:37547]
[..]
RIP: 0010:nft_chain_validate+0xcb/0x110 [nf_tables]
[..]
nft_immediate_validate+0x36/0x50 [nf_tables]
nft_chain_validate+0xc9/0x110 [nf_tables]
nft_immediate_validate+0x36/0x50 [nf_tables]
nft_chain_validate+0xc9/0x110 [nf_tables]
nft_immediate_validate+0x36/0x50 [nf_tables]
nft_chain_validate+0xc9/0x110 [nf_tables]
nft_immediate_validate+0x36/0x50 [nf_tables]
nft_chain_validate+0xc9/0x110 [nf_tables]
nft_immediate_validate+0x36/0x50 [nf_tables]
nf
Wiz
CVE-2025-68167 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68167 CVE-2025-68167 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68167 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gpiolib: fix invalid pointer access in debugfs
If the memory allocation in gpiolib_seq_start() fails, the s->private
field remains uninitialized and is later dereferenced without checking
in gpiolib_seq_stop(). Initialize s->private to NULL before calling
kzalloc() and check it before dereferencing it.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-core
ksel
Wiz
CVE-2023-54222 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54222 CVE-2023-54222 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54222 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hte: tegra-194: Fix off by one in tegra_hte_map_to_line_id()
The "map_sz" is the number of elements in the "m" array so the >
comparison needs to be changed to >= to prevent an out of bounds
read.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-modules-partner
kernel-rt-modules
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added a
Wiz
CVE-2025-68206 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68206 CVE-2025-68206 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68206 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_ct: add seqadj extension for natted connections
Sequence adjustment may be required for FTP traffic with PASV/EPSV modes.
due to need to re-write packet payload (IP, port) on the ftp control
connection. This can require changes to the TCP length and expected
seq / ack_seq.
The easiest way to reproduce this issue is with PASV mode.
Example ruleset:
table inet ftp_nat {
ct helper ftp_helper {
type "ftp" protocol tcp
l3proto inet
}
chain prerouting {
type filter hook prerouting priority 0; policy accept;
tcp dport 21 ct state new ct helper set "ftp_helper"
}
}
table ip nat {
chain prerouting {
type nat hook prerouting priority -100; p
Wiz
CVE-2025-68784 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68784 CVE-2025-68784 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68784 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: fix a UAF problem in xattr repair
The xchk_setup_xattr_buf function can allocate a new value buffer, which
means that any reference to ab->value before the call could become a
dangling pointer. Fix this by moving an assignment to after the buffer
setup.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
perf6.12
cluster-md-kmp-azure
Sources
NVD
Debian 13, 14 Has Fix Added
Wiz
CVE-2025-71087 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71087 [MEDIUM] CVE-2025-71087 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71087 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iavf: fix off-by-one issues in iavf_config_rss_reg()
There are off-by-one bugs when configuring RSS hash key and lookup
table, causing out-of-bounds reads to memory [1] and out-of-bounds
writes to device registers.
Before commit 43a3d9ba34c9 ("i40evf: Allow PF driver to configure RSS"),
the loop upper bounds were:
i <= I40E_VFQF_{HKEY,HLUT}_MAX_INDEX
which is safe since the value is the last valid index.
rss_{key,lut}_size / 4
(rss_{key,lut}_size / 4) - 1
<=
<
<=
[1] KASAN splat about rss_key_size off-by-one
BUG: KASAN: slab-out-of-bounds in iavf_config_rss+0x619/0x800
Read of size 4 at addr ffff888102c50134 by task kworker/u8:6/63
CPU: 0 UI
Wiz
CVE-2025-68248 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68248 CVE-2025-68248 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68248 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vmw_balloon: indicate success when effectively deflating during migration
When migrating a balloon page, we first deflate the old page to then
inflate the new page.
However, if inflating the new page succeeded, we effectively deflated the
old page, reducing the balloon size.
In that case, the migration actually worked: similar to migrating+
immediately deflating the new page. The old page will be freed back to
the buddy.
Right now, the core will leave the page be marked as isolated (as we
returned an error). When later trying to putback that page, we will run
into the WARN_ON_ONCE() in balloon_page_putback().
That handling was changed in commit
Wiz
CVE-2026-23449 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23449 CVE-2026-23449 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23449 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: teql: Fix double-free in teql_master_xmit
Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should
be called using the seq_lock to avoid racing with the datapath. Failure
to do so may cause crashes like the following:
[ 238.028993][ T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139)
[ 238.029328][ T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318
[ 238.029749][ T318]
[ 238.029900][ T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full)
[ 238.029906][ T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 238.029910][ T318] Call T
Wiz
CVE-2023-54322 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54322 CVE-2023-54322 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54322 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: set __exception_irq_entry with __irq_entry as a default
filter_irq_stacks() is supposed to cut entries which are related irq entries
from its call stack.
And in_irqentry_text() which is called by filter_irq_stacks()
uses __irqentry_text_start/end symbol to find irq entries in callstack.
But it doesn't work correctly as without "CONFIG_FUNCTION_GRAPH_TRACER",
arm64 kernel doesn't include gic_handle_irq which is entry point of arm64 irq
between __irqentry_text_start and __irqentry_text_end as we discussed in below link. https://lore.kernel.org/all/CACT4Y+aReMGLYua2rCLHgFpS9io5cZC04Q8GLs-uNmrn1ezxYQ@mail.gmail.com/#t
This problem can makes uni
Wiz
CVE-2025-68378 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68378 CVE-2025-68378 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68378 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix stackmap overflow check in __bpf_get_stackid()
Syzkaller reported a KASAN slab-out-of-bounds write in __bpf_get_stackid()
when copying stack trace data. The issue occurs when the perf trace
contains more stack entries than the stack map bucket can hold,
leading to an out-of-bounds write in the bucket's data array.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affec
Wiz
CVE-2023-54215 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54215 CVE-2023-54215 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54215 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
virtio-vdpa: Fix cpumask memory leak in virtio_vdpa_find_vqs()
Free the cpumask allocated by create_affinity_masks() before returning
from the function.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-devel-matched
kernel-zfcpdump-modules
Sources
NVD
Debian 13, 14 Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW Has Fix Added at: Dec 31, 2025
Ubuntu 16.04
Wiz
CVE-2023-54045 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54045 CVE-2023-54045 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54045 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
audit: fix possible soft lockup in __audit_inode_child()
Tracefs or debugfs maybe cause hundreds to thousands of PATH records,
too many PATH records maybe cause soft lockup.
For example:
CONFIG_KASAN=y && CONFIG_PREEMPTION=n
auditctl -a exit,always -S open -k key
sysctl -w kernel.watchdog_thresh=5
mkdir /sys/kernel/debug/tracing/instances/test
There may be a soft lockup as follows:watchdog: BUG: soft lockup - CPU#45 stuck for 7s! [mkdir:15498]Kernel panic - not syncing: softlockup: hung tasksCall trace:
dump_backtrace+0x0/0x30c
show_stack+0x20/0x30
dump_stack+0x11c/0x174
panic+0x27c/0x494
watchdog_timer_fn+0x2bc/0x390
__run_hrtimer+0x148/0x4fc
Wiz
CVE-2025-68306 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68306 CVE-2025-68306 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68306 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: btusb: mediatek: Fix kernel crash when releasing mtk iso interface
When performing reset tests and encountering abnormal card drop issues
that lead to a kernel crash, it is necessary to perform a null check
before releasing resources to avoid attempting to release a null pointer.
[ 29.158070] Hardware name: Google Quigon sku196612/196613 board (DT)
[ 29.158076] Workqueue: hci0 hci_cmd_sync_work [bluetooth]
[ 29.158154] pstate: 20400009 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 29.158162] pc : klist_remove+0x90/0x158
[ 29.158174] lr : klist_remove+0x88/0x158
[ 29.158180] sp : ffffffc0846b3c00
[ 29.158185] pmr_save: 000000e0
[ 29.15
Wiz
CVE-2023-54049 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54049 CVE-2023-54049 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54049 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rpmsg: glink: Add check for kstrdup
Add check for the return value of kstrdup() and return the error
if it fails in order to avoid NULL pointer dereference.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-freescale
dtb-mediatek
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Ubuntu 16.04 Severity MEDIUM No Fix Add
Wiz
CVE-2025-71156 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71156 [HIGH] CVE-2025-71156 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71156 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gve: defer interrupt enabling until NAPI registration
Currently, interrupts are automatically enabled immediately upon
request. This allows interrupt to fire before the associated NAPI
context is fully initialized and cause failures like below:
[ 0.946369] Call Trace:
[ 0.946369] [ 0.946369] __napi_poll+0x2a/0x1e0
[ 0.946369] net_rx_action+0x2f9/0x3f0
[ 0.946369] handle_softirqs+0xd6/0x2c0
[ 0.946369] ? handle_edge_irq+0xc1/0x1b0
[ 0.946369] __irq_exit_rcu+0xc3/0xe0
[ 0.946369] common_interrupt+0x81/0xa0
[ 0.946369] [ 0.946369] [ 0.946369] asm_common_interrupt+0x22/0x40
[ 0.946369] RIP: 0010:pv_native_safe_halt+0xb/0x10
IRQF_NO_AUTOEN
This ensure
Wiz
CVE-2023-54286 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54286 CVE-2023-54286 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54286 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: iwlwifi: dvm: Fix memcpy: detected field-spanning write backtrace
A received TKIP key may be up to 32 bytes because it may contain
MIC rx/tx keys too. These are not used by iwl and copying these
over overflows the iwl_keyinfo.key field.
Add a check to not copy more data to iwl_keyinfo.key then will fit.
This fixes backtraces like this one:
memcpy: detected field-spanning write (size 32) of single field "sta_cmd.key.key" at drivers/net/wireless/intel/iwlwifi/dvm/sta.c:1103 (size 16)
WARNING: CPU: 1 PID: 946 at drivers/net/wireless/intel/iwlwifi/dvm/sta.c:1103 iwlagn_send_sta_key+0x375/0x390 [iwldvm] Hardware name: Dell Inc. Latitude E6430/0H
Wiz
CVE-2025-71266 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71266 CVE-2025-71266 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71266 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: ntfs3: check return value of indx_find to avoid infinite loop
We found an infinite loop bug in the ntfs3 file system that can lead to a
Denial-of-Service (DoS) condition.
A malformed dentry in the ntfs3 filesystem can cause the kernel to hang
during the lookup operations. By setting the HAS_SUB_NODE flag in an
INDEX_ENTRY within a directory's INDEX_ALLOCATION block and manipulating the
VCN pointer, an attacker can cause the indx_find() function to repeatedly
read the same block, allocating 4 KB of memory each time. The kernel lacks
VCN loop detection and depth limits, causing memory exhaustion and an OOM
crash.
This patch adds a return value c
Wiz
CVE-2026-23111 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23111 [HIGH] CVE-2026-23111 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23111 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: fix inverted genmask check in nft_map_catchall_activate()
nft_map_catchall_activate() has an inverted element activity check
compared to its non-catchall counterpart nft_mapelem_activate() and
compared to what is logically required.
nft_map_catchall_activate() is called from the abort path to re-activate
catchall map elements that were deactivated during a failed transaction.
It should skip elements that are already active (they don't need
re-activation) and process elements that are inactive (they need to be
restored). Instead, the current code does the opposite: it skips inactive
elements and processes active ones.
Compare
Wiz
CVE-2026-23252 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23252 CVE-2026-23252 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23252 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: get rid of the xchk_xfile_*_descr calls
The xchk_xfile_*_descr macros call kasprintf, which can fail to allocate
memory if the formatted string is larger than 16 bytes (or whatever the
nofail guarantees are nowadays). Some of them could easily exceed that,
and Jiaming Zhang found a few places where that can happen with syzbot.
The descriptions are debugging aids and aren't required to be unique, so
let's just pass in static strings and eliminate this path to failure.
Note this patch touches a number of commits, most of which were merged
between 6.6 and 6.14.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux K
Wiz
CVE-2023-54273 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54273 CVE-2023-54273 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54273 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix leak of dev tracker
At the stage of direction checks, the netdev reference tracker is
already initialized, but released with wrong *_put() call.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
bpftool
kernel-cross-headers
Sources
NVD
Red Hat 9 Severity MEDIUM Has Fix Added at: Dec 31, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Jan 02, 2026
Wiz
CVE-2022-50769 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50769 CVE-2022-50769 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50769 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: mxcmmc: fix return value check of mmc_add_host()
mmc_add_host() may return error, if we ignore its return value, the memory
that allocated in mmc_alloc_host() will be leaked and it will lead a kernel
crash because of deleting not added device in the remove path.
So fix this by checking the return value and goto error path which will call
mmc_free_host().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Wiz
CVE-2026-23317 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23317 [HIGH] CVE-2026-23317 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23317 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/vmwgfx: Return the correct value in vmw_translate_ptr functions
Before the referenced fixes these functions used a lookup function that
returned a pointer. This was changed to another lookup function that
returned an error code with the pointer becoming an out parameter.
The error path when the lookup failed was not changed to reflect this
change and the code continued to return the PTR_ERR of the now
uninitialized pointer. This could cause the vmw_translate_ptr functions
to return success when they actually failed causing further uninitialized
and OOB accesses.
Source : NVD
## 7.8
Score
Published March 25, 2026
Severity HIGH
CNA Score
Wiz
CVE-2022-50851 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50851 CVE-2022-50851 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50851 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vhost_vdpa: fix the crash in unmap a large memory
While testing in vIOMMU, sometimes Guest will unmap very large memory,
which will cause the crash. To fix this, add a new function
vhost_vdpa_general_unmap(). This function will only unmap the memory
that saved in iotlb.
Call Trace:
[ 647.820144] ------------[ cut here ]------------
[ 647.820848] kernel BUG at drivers/iommu/intel/iommu.c:1174!
[ 647.821486] invalid opcode: 0000 [#1] PREEMPT SMP PTI
[ 647.822082] CPU: 10 PID: 1181 Comm: qemu-system-x86 Not tainted 6.0.0-rc1home_lulu_2452_lulu7_vhost+ #62
[ 647.823139] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-29-g6a62e0cb0df
Wiz
CVE-2023-54248 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54248 CVE-2023-54248 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54248 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Add check for kmemdup
Since the kmemdup may return NULL pointer,
it should be better to add check for the return value
in order to avoid NULL pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-oracle-5.15
bpftool
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Ubuntu 16.04, 18.04 Severity
Wiz
CVE-2022-50761 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50761 CVE-2022-50761 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50761 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/xen: Fix memory leak in xen_init_lock_cpu()
In xen_init_lock_cpu(), the @name has allocated new string by kasprintf(),
if bind_ipi_to_irqhandler() fails, it should be freed, otherwise may lead
to a memory leak issue, fix it.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 20.3
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-livepatch-5.10.165-143.735
linux-hwe
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: D
Wiz
CVE-2025-71066 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71066 CVE-2025-71066 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71066 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: ets: Always remove class from active list before deleting in ets_qdisc_change
[email protected] says:
ets_qdisc_dequeue
ets_qdisc_change
struct Qdisc
Analysis:
static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
...
// (1) this lock is preventing .change handler (`ets_qdisc_change`)
//to race with .dequeue handler (`ets_qdisc_dequeue`)
sch_tree_lock(sch);
for (i = nbands; i = q->nstrict && q->classes[i].qdisc->q.qlen)
list_del_init(&q->classes[i].alist);
qdisc_purge_queue(q->classes[i].qdisc);
}
WRITE_ONCE(q->nbands, nbands);
for (i = nstrict; i nstrict; i++) {
if (q->c
Wiz
CVE-2026-23121 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23121 [MEDIUM] CVE-2026-23121 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23121 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mISDN: annotate data-race around dev->work
dev->work can re read locklessly in mISDN_read()
and mISDN_poll(). Add READ_ONCE()/WRITE_ONCE() annotations.
BUG: KCSAN: data-race in mISDN_ioctl / mISDN_read
write to 0xffff88812d848280 of 4 bytes by task 10864 on cpu 1:
misdn_add_timer drivers/isdn/mISDN/timerdev.c:175 [inline]
mISDN_ioctl+0x2fb/0x550 drivers/isdn/mISDN/timerdev.c:233
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:597 [inline]
__se_sys_ioctl+0xce/0x140 fs/ioctl.c:583
__x64_sys_ioctl+0x43/0x50 fs/ioctl.c:583
x64_sys_call+0x14b0/0x3000 arch/x86/include/generated/asm/syscalls_64.h:17
do_syscall_x64 arch/x86/entry/syscall_64.c:6
Wiz
CVE-2025-68324 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68324 CVE-2025-68324 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68324 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: imm: Fix use-after-free bug caused by unfinished delayed work
The delayed work item 'imm_tq' is initialized in imm_attach() and
scheduled via imm_queuecommand() for processing SCSI commands. When the
IMM parallel port SCSI host adapter is detached through imm_detach(),
the imm_struct device instance is deallocated.
However, the delayed work might still be pending or executing
when imm_detach() is called, leading to use-after-free bugs
when the work function imm_interrupt() accesses the already
freed imm_struct memory.
The race condition can occur as follows:
CPU 0(detach thread) | CPU 1
| imm_queuecommand()
| imm_queuecommand_lck()
imm_deta
Wiz
CVE-2023-54140 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54140 CVE-2023-54140 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54140 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nilfs2: fix WARNING in mark_buffer_dirty due to discarded buffer reuse
A syzbot stress test using a corrupted disk image reported that
mark_buffer_dirty() called from __nilfs_mark_inode_dirty() or
nilfs_palloc_commit_alloc_entry() may output a kernel warning, and can
panic if the kernel is booted with panic_on_warn.
This is because nilfs2 keeps buffer pointers in local structures for some
metadata and reuses them, but such buffers may be forcibly discarded by
nilfs_clear_dirty_page() in some critical situations.
This issue is reported to appear after commit 28a65b49eb53 ("nilfs2: do
not write dirty data after degenerating to read-only"), but the i
Wiz
CVE-2026-23136 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-23136 [HIGH] CVE-2026-23136 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23136 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: reset sparse-read state in osd_fault()
When a fault occurs, the connection is abandoned, reestablished, and any
pending operations are retried. The OSD client tracks the progress of a
sparse-read reply using a separate state machine, largely independent of
the messenger's state.
If a connection is lost mid-payload or the sparse-read state machine
returns an error, the sparse-read state is not reset. The OSD client
will then interpret the beginning of a new reply as the continuation of
the old one. If this makes the sparse-read machinery enter a failure
state, it may never recover, producing loops like:
libceph: [0] got 0 extents
libceph:
Wiz
CVE-2023-54265 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54265 CVE-2023-54265 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54265 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: Fix an uninit variable access bug in __ip6_make_skb()
Syzbot reported a bug as following:
BUG: KMSAN: uninit-value in arch_atomic64_inc arch/x86/include/asm/atomic64_64.h:88 [inline]
BUG: KMSAN: uninit-value in arch_atomic_long_inc include/linux/atomic/atomic-long.h:161 [inline]
BUG: KMSAN: uninit-value in atomic_long_inc include/linux/atomic/atomic-instrumented.h:1429 [inline]
BUG: KMSAN: uninit-value in __ip6_make_skb+0x2f37/0x30f0 net/ipv6/ip6_output.c:1956
arch_atomic64_inc arch/x86/include/asm/atomic64_64.h:88 [inline]
arch_atomic_long_inc include/linux/atomic/atomic-long.h:161 [inline]
atomic_long_inc include/linux/atomic/atomic-instrum
Wiz
CVE-2025-68180 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68180 CVE-2025-68180 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68180 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amd/display: Fix NULL deref in debugfs odm_combine_segments
When a connector is connected but inactive (e.g., disabled by desktop
environments), pipe_ctx->stream_res.tg will be destroyed. Then, reading
odm_combine_segments causes kernel NULL pointer dereference.
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 16 UID: 0 PID: 26474 Comm: cat Not tainted 6.17.0+ #2 PREEMPT(lazy) e6a17af9ee6db7c63e9d90dbe5b28ccab67520c6
Hardware name: LENOVO 21Q4/LNVNB161216, BIOS PXCN25WW 03/27/2025
RIP: 0010:odm_co
Wiz
CVE-2025-68813 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68813 CVE-2025-68813 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68813 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipvs: fix ipv4 null-ptr-deref in route error path
The IPv4 code path in __ip_vs_get_out_rt() calls dst_link_failure()
without ensuring skb->dev is set, leading to a NULL pointer dereference
in fib_compute_spec_dst() when ipv4_link_failure() attempts to send
ICMP destination unreachable messages.
The issue emerged after commit ed0de45a1008 ("ipv4: recompile ip options
in ipv4_link_failure") started calling __ip_options_compile() from
ipv4_link_failure(). This code path eventually calls fib_compute_spec_dst()
which dereferences skb->dev. An attempt was made to fix the NULL skb->dev
dereference in commit 0113d9c9d1cc ("ipv4: fix null-deref in
ipv4_lin
Wiz
CVE-2023-54106 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54106 CVE-2023-54106 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54106 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5: fix potential memory leak in mlx5e_init_rep_rx
The memory pointed to by the priv->rx_res pointer is not freed in the error
path of mlx5e_init_rep_rx, which can lead to a memory leak. Fix by freeing
the memory in the error path, thereby making the error path identical to
mlx5e_cleanup_rep_rx().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-mediatek
kernel-64k-d
Wiz
CVE-2025-68775 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68775 CVE-2025-68775 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68775 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/handshake: duplicate handshake cancellations leak socket
When a handshake request is cancelled it is removed from the
handshake_net->hn_requests list, but it is still present in the
handshake_rhashtbl until it is destroyed.
If a second cancellation request arrives for the same handshake request,
then remove_pending() will return false... and assuming
HANDSHAKE_F_REQ_COMPLETED isn't set in req->hr_flags, we'll continue
processing through the out_true label, where we put another reference on
the sock and a refcount underflow occurs.
This can happen for example if a handshake times out - particularly if
the SUNRPC client sends the AUTH_TLS probe
Wiz
CVE-2025-68208 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68208 CVE-2025-68208 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68208 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: account for current allocated stack depth in widen_imprecise_scalars()
The usage pattern for widen_imprecise_scalars() looks as follows:
prev_st = find_prev_entry(env, ...);
queued_st = push_stack(...);
widen_imprecise_scalars(env, prev_st, queued_st);
Where prev_st is an ancestor of the queued_st in the explored states
tree. This ancestor is not guaranteed to have same allocated stack
depth as queued_st. E.g. in the following case:
def main():
for i in 1..2:
foo(i) // same callsite, differnt param
def foo(i):
if i == 1:
use 128 bytes of stack
iterator based loop
Here, for a second 'foo' call prev_st->allocated_stack is 128,
while queued_s
Wiz
CVE-2023-54310 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54310 CVE-2023-54310 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54310 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: message: mptlan: Fix use after free bug in mptlan_remove() due to race condition
mptlan_probe() calls mpt_register_lan_device() which initializes the
&priv->post_buckets_task workqueue. A call to
mpt_lan_wake_post_buckets_task() will subsequently start the work.
During driver unload in mptlan_remove() the following race may occur:
CPU0 CPU1
|mpt_lan_post_receive_buckets_work()
mptlan_remove() |
free_netdev() |
kfree(dev); |
|
| dev->mtu
| //use
Fix this by finishing the work prior to cleaning up in mptlan_remove().
[mkp: we really should remove mptlan instead of attempting to fix it]
Source : NVD
Published December 30, 2025
CNA Score
Wiz
CVE-2026-23418 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23418 CVE-2026-23418 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23418 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/reg_sr: Fix leak on xa_store failure
Free the newly allocated entry when xa_store() fails to avoid a memory
leak on the error path.
v2: use goto fail_free. (Bala)
(cherry picked from commit 6bc6fec71ac45f52db609af4e62bdb96b9f5fadb)
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-devel-matched
kernel-64k-modules-extra
Sources
NVD
Debian 14 Has Fix Added at: Ap
Wiz
CVE-2025-68748 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68748 CVE-2025-68748 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68748 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/panthor: Fix UAF race between device unplug and FW event processing
The function panthor_fw_unplug() will free the FW memory sections.
The problem is that there could still be pending FW events which are yet
not handled at this point. process_fw_events_work() can in this case try
to access said freed memory.
Simply call disable_work_sync() to both drain and prevent future
invocation of process_fw_events_work().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perc
Wiz
CVE-2026-23173 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23173 [MEDIUM] CVE-2026-23173 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23173 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: TC, delete flows only for existing peers
When deleting TC steering flows, iterate only over actual devcom
peers instead of assuming all possible ports exist. This avoids
touching non-existent peers and ensures cleanup is limited to
devices the driver is currently connected to.
BUG: kernel NULL pointer dereference, address: 0000000000000008
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 133c8a067 P4D 0
Oops: Oops: 0002 [#1] SMP
CPU: 19 UID: 0 PID: 2169 Comm: tc Not tainted 6.18.0+ #156 NONE
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/0
Wiz
CVE-2025-68252 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68252 CVE-2025-68252 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68252 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
misc: fastrpc: Fix dma_buf object leak in fastrpc_map_lookup
In fastrpc_map_lookup, dma_buf_get is called to obtain a reference to
the dma_buf for comparison purposes. However, this reference is never
released when the function returns, leading to a dma_buf memory leak.
Fix this by adding dma_buf_put before returning from the function,
ensuring that the temporarily acquired reference is properly released
regardless of whether a matching map is found.
Rule: add
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2023-54199 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54199 CVE-2023-54199 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54199 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/adreno: Fix null ptr access in adreno_gpu_cleanup()
Fix the below kernel panic due to null pointer access:
[ 18.504431] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000048
[ 18.513464] Mem abort info:
[ 18.516346] ESR = 0x0000000096000005
[ 18.520204] EC = 0x25: DABT (current EL), IL = 32 bits
[ 18.525706] SET = 0, FnV = 0
[ 18.528878] EA = 0, S1PTW = 0
[ 18.532117] FSC = 0x05: level 1 translation fault
[ 18.537138] Data abort info:
[ 18.540110] ISV = 0, ISS = 0x00000005
[ 18.544060] CM = 0, WnR = 0
[ 18.547109] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000112826000
[ 18.553738] [0000000000000048] pgd=0000
Wiz
CVE-2022-50712 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50712 CVE-2022-50712 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50712 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
devlink: hold region lock when flushing snapshots
Netdevsim triggers a splat on reload, when it destroys regions
with snapshots pending:
WARNING: CPU: 1 PID: 787 at net/core/devlink.c:6291 devlink_region_snapshot_del+0x12e/0x140
CPU: 1 PID: 787 Comm: devlink Not tainted 6.1.0-07460-g7ae9888d6e1c #580
RIP: 0010:devlink_region_snapshot_del+0x12e/0x140
Call Trace: devl_region_destroy+0x70/0x140
nsim_dev_reload_down+0x2f/0x60 [netdevsim]
devlink_reload+0x1f7/0x360
devlink_nl_cmd_reload+0x6ce/0x860
genl_family_rcv_msg_doit.isra.0+0x145/0x1c0
This is the locking assert in devlink_region_snapshot_del(),
we're supposed to be holding the region->snapshot_l
Wiz
CVE-2023-53846 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53846 CVE-2023-53846 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53846 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
f2fs: fix to do sanity check on direct node in truncate_dnode()
syzbot reports below bug:
BUG: KASAN: slab-use-after-free in f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574
Read of size 4 at addr ffff88802a25c000 by task syz-executor148/5000
CPU: 1 PID: 5000 Comm: syz-executor148 Not tainted 6.4.0-rc7-syzkaller-00041-ge660abd551f1 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023
Call Trace: __dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106
print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351
print_report mm/kasan/report.c:462 [inli
Wiz
CVE-2022-50835 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50835 CVE-2022-50835 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50835 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
jbd2: add miss release buffer head in fc_do_one_pass()
In fc_do_one_pass() miss release buffer head after use which will lead
to reference count leak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gcp-5.4
linux-ibm-5.4
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6, 7, 8 Severity LOW No Fix Added at:
Wiz
CVE-2026-23071 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23071 [MEDIUM] CVE-2026-23071 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23071 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regmap: Fix race condition in hwspinlock irqsave routine
Previously, the address of the shared member '&map->spinlock_flags' was
passed directly to 'hwspin_lock_timeout_irqsave'. This creates a race
condition where multiple contexts contending for the lock could overwrite
the shared flags variable, potentially corrupting the state for the
current lock owner.
Fix this by using a local stack variable 'flags' to store the IRQ state
temporarily.
Source : NVD
## 4.7
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Dat
Wiz
CVE-2025-68229 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68229 CVE-2025-68229 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68229 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: tcm_loop: Fix segfault in tcm_loop_tpg_address_show()
If the allocation of tl_hba->sh fails in tcm_loop_driver_probe() and we
attempt to dereference it in tcm_loop_tpg_address_show() we will get a
segfault, see below for an example. So, check tl_hba->sh before
dereferencing it.
Unable to allocate struct scsi_host
BUG: kernel NULL pointer dereference, address: 0000000000000194
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 1 PID: 8356 Comm: tokio-runtime-w Not tainted 6.6.104.2-4.azl3 #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual
Wiz
CVE-2025-68217 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68217 CVE-2025-68217 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68217 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Input: pegasus-notetaker - fix potential out-of-bounds access
In the pegasus_notetaker driver, the pegasus_probe() function allocates
the URB transfer buffer using the wMaxPacketSize value from
the endpoint descriptor. An attacker can use a malicious USB descriptor
to force the allocation of a very small buffer.
Subsequently, if the device sends an interrupt packet with a specific
pattern (e.g., where the first byte is 0x80 or 0x42),
the pegasus_parse_packet() function parses the packet without checking
the allocated buffer size. This leads to an out-of-bounds memory access.
Source : NVD
## 5.7
Score
Published December 16, 2025
Severity MEDI
Wiz
CVE-2026-23465 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23465 CVE-2026-23465 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23465 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: log new dentries when logging parent dir of a conflicting inode
If we log the parent directory of a conflicting inode, we are not logging
the new dentries of the directory, so when we finish we have the parent
directory's inode marked as logged but we did not log its new dentries.
As a consequence if the parent directory is explicitly fsynced later and
it does not have any new changes since we logged it, the fsync is a no-op
and after a power failure the new dentries are missing.
Example scenario:
$ mkdir foo
$ sync
$rmdir foo
$ mkdir dir1
$ mkdir dir2
## A file with the same name and parent as the directory we just deleted
## and wa
Wiz
CVE-2025-71123 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71123 [HIGH] CVE-2025-71123 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71123 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix string copying in parse_apply_sb_mount_options()
strscpy_pad() can't be used to copy a non-NUL-term string into a NUL-term
string of possibly bigger size. Commit 0efc5990bca5 ("string.h: Introduce
memtostr() and memtostr_pad()") provides additional information in that
regard. So if this happens, the following warning is observed:
strnlen: detected buffer overflow: 65 byte read of buffer size 64
WARNING: CPU: 0 PID: 28655 at lib/string_helpers.c:1032 __fortify_report+0x96/0xc0 lib/string_helpers.c:1032
Modules linked in:
CPU: 0 UID: 0 PID: 28655 Comm: syz-executor.3 Not tainted 6.12.54-syzkaller-00144-g5f0270f1ba00 #0
Hardware name: QEMU S
Wiz
CVE-2023-54316 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54316 CVE-2023-54316 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54316 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
refscale: Fix uninitalized use of wait_queue_head_t
Running the refscale test occasionally crashes the kernel with the
following error:
[ 8569.952896] BUG: unable to handle page fault for address: ffffffffffffffe8
[ 8569.952900] #PF: supervisor read access in kernel mode
[ 8569.952902] #PF: error_code(0x0000) - not-present page
[ 8569.952904] PGD c4b048067 P4D c4b049067 PUD c4b04b067 PMD 0
[ 8569.952910] Oops: 0000 [#1] PREEMPT_RT SMP NOPTI
[ 8569.952916] Hardware name: Dell Inc. PowerEdge R750/0WMWCR, BIOS 1.2.4 05/28/2021
[ 8569.952917] RIP: 0010:prepare_to_wait_event+0x101/0x190
:
[ 8569.952940] Call Trace:
[ 8569.952941] [ 8569.952944] ref_scal
Wiz
CVE-2025-40362 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40362 CVE-2025-40362 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40362 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ceph: fix multifs mds auth caps issue
The mds auth caps check should also validate the
fsname along with the associated caps. Not doing
so would result in applying the mds auth caps of
one fs on to the other fs in a multifs ceph cluster.
The bug causes multiple issues w.r.t user
authentication, following is one such example.
Steps to Reproduce (on vstart cluster):
Create two file systems in a cluster, say 'fsname1' and 'fsname2'
Authorize read only permission to the user 'client.usr' on fs 'fsname1' $ceph fs authorize fsname1 client.usr / r
Authorize read and write permission to the same user 'client.usr' on fs 'fsname2' $ceph fs authorize fsnam
Wiz
CVE-2025-71143 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71143 [HIGH] CVE-2025-71143 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71143 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clk: samsung: exynos-clkout: Assign .num before accessing .hws
Commit f316cdff8d67 ("clk: Annotate struct clk_hw_onecell_data with
__counted_by") annotated the hws member of 'struct clk_hw_onecell_data'
with __counted_by, which informs the bounds sanitizer (UBSAN_BOUNDS)
about the number of elements in .hws[], so that it can warn when .hws[]
is accessed out of bounds. As noted in that change, the __counted_by
member must be initialized with the number of elements before the first
array access happens, otherwise there will be a warning from each access
prior to the initialization because the number of elements is zero. This
occurs in exynos_clkout_pr
Wiz
CVE-2026-23278 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23278 [HIGH] CVE-2026-23278 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23278 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: always walk all pending catchall elements
During transaction processing we might have more than one catchall element:
1 live catchall element and 1 pending element that is coming as part of the
new batch.
If the map holding the catchall elements is also going away, its
required to toggle all catchall elements and not just the first viable
candidate.
Otherwise, we get:
WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404
RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables]
[..]
__nft_set_elem_destroy+0x106/0x380 [nf_tables]
nf_tables_abort_release+0x348/0x8d0 [nf_tables]
nf_t
Wiz
CVE-2022-50886 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50886 CVE-2022-50886 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50886 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: toshsd: fix return value check of mmc_add_host()
mmc_add_host() may return error, if we ignore its return value, the memory
that allocated in mmc_alloc_host() will be leaked and it will lead a kernel
crash because of deleting not added device in the remove path.
So fix this by checking the return value and goto error path which will call
mmc_free_host(), besides, free_irq() also needs be called.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 1
Wiz
CVE-2023-54114 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54114 CVE-2023-54114 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54114 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: nsh: Use correct mac_offset to unwind gso skb in nsh_gso_segment()
As the call trace shows, skb_panic was caused by wrong skb->mac_header
in nsh_gso_segment():
invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI
CPU: 3 PID: 2737 Comm: syz Not tainted 6.3.0-next-20230505 #1
RIP: 0010:skb_panic+0xda/0xe0
call Trace:
skb_push+0x91/0xa0
nsh_gso_segment+0x4f3/0x570
skb_mac_gso_segment+0x19e/0x270
__skb_gso_segment+0x1e8/0x3c0
validate_xmit_skb+0x452/0x890
validate_xmit_skb_list+0x99/0xd0
sch_direct_xmit+0x294/0x7c0
__dev_queue_xmit+0x16f0/0x1d70
packet_xmit+0x185/0x210
packet_snd+0xc15/0x1170
packet_sendmsg+0x7b/0xa0
sock_sendmsg+0x14f/0x160
The root
Wiz
CVE-2026-23441 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23441 CVE-2026-23441 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23441 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Prevent concurrent access to IPSec ASO context
The query or updating IPSec offload object is through Access ASO WQE.
The driver uses a single mlx5e_ipsec_aso struct for each PF, which
contains a shared DMA-mapped context for all ASO operations.
A race condition exists because the ASO spinlock is released before
the hardware has finished processing WQE. If a second operation is
initiated immediately after, it overwrites the shared context in the
DMA area.
When the first operation's completion is processed later, it reads
this corrupted context, leading to unexpected behavior and incorrect
results.
This commit fixes the race by introduci
Wiz
CVE-2023-54013 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54013 CVE-2023-54013 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54013 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
interconnect: Fix locking for runpm vs reclaim
For cases where icc_bw_set() can be called in callbaths that could
deadlock against shrinker/reclaim, such as runpm resume, we need to
decouple the icc locking. Introduce a new icc_bw_lock for cases where
we need to serialize bw aggregation and update to decouple that from
paths that require memory allocation such as node/link creation/
destruction.
Fixes this lockdep splat:
## ======================================================
WARNING: possible circular locking dependency detected
6.2.0-rc8-debug+ #554 Not tainted
ring0/132 is trying to acquire lock:
ffffff80871916d0 (&gmu->lock){+.+.}-{3:3},
Wiz
CVE-2023-54026 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54026 CVE-2023-54026 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54026 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
opp: Fix use-after-free in lazy_opp_tables after probe deferral
When dev_pm_opp_of_find_icc_paths() in _allocate_opp_table() returns
-EPROBE_DEFER, the opp_table is freed again, to wait until all the
interconnect paths are available.
However, if the OPP table is using required-opps then it may already
have been added to the global lazy_opp_tables list. The error path
does not remove the opp_table from the list again.
This can cause crashes later when the provider of the required-opps
is added, since we will iterate over OPP tables that have already been
freed. E.g.:
Unable to handle kernel NULL pointer dereference when read
CPU: 0 PID: 7 Comm: kw
Wiz
CVE-2026-23221 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23221 [HIGH] CVE-2026-23221 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23221 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bus: fsl-mc: fix use-after-free in driver_override_show()
The driver_override_show() function reads the driver_override string
without holding the device_lock. However, driver_override_store() uses
driver_set_override(), which modifies and frees the string while holding
the device_lock.
This can result in a concurrent use-after-free if the string is freed
by the store function while being read by the show function.
Fix this by holding the device_lock around the read operation.
Source : NVD
## 7.8
Score
Published February 18, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA
Wiz
CVE-2023-54204 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54204 CVE-2023-54204 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54204 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: sunplus: fix return value check of mmc_add_host()
mmc_add_host() may return error, if we ignore its return value,
the memory allocated in mmc_alloc_host() will be leaked
null-ptr-deref will happen when calling mmc_remove_host()in remove function spmmc_drv_remove() because deleting notadded device.
Fix this by checking the return value of mmc_add_host(). Moreover,
I fixed the error handling path of spmmc_drv_probe() to clean up.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitat
Wiz
CVE-2023-54020 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54020 CVE-2023-54020 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54020 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: sf-pdma: pdma_desc memory leak fix
Commit b2cc5c465c2c ("dmaengine: sf-pdma: Add multithread support for a
DMA channel") changed sf_pdma_prep_dma_memcpy() to unconditionally
allocate a new sf_pdma_desc each time it is called.
The driver previously recycled descs, by checking the in_use flag, only
allocating additional descs if the existing one was in use. This logic
was removed in commit b2cc5c465c2c ("dmaengine: sf-pdma: Add multithread
support for a DMA channel"), but sf_pdma_free_desc() was not changed to
handle the new behaviour.
As a result, each time sf_pdma_prep_dma_memcpy() is called, the previous
descriptor is leaked, over time
Wiz
CVE-2025-68783 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68783 CVE-2025-68783 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68783 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: usb-mixer: us16x08: validate meter packet indices
get_meter_levels_from_urb() parses the 64-byte meter packets sent by
the device and fills the per-channel arrays meter_level[],
comp_level[] and master_level[] in struct snd_us16x08_meter_store.
Currently the function derives the channel index directly from the
meter packet (MUB2(meter_urb, s) - 1) and uses it to index those
arrays without validating the range. If the packet contains a
negative or out-of-range channel number, the driver may write past
the end of these arrays.
Introduce a local channel variable and validate it before updating the
arrays. We reject negative indices, limit meter
Wiz
CVE-2025-68372 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68372 CVE-2025-68372 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68372 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nbd: defer config put in recv_work
There is one uaf issue in recv_work when running NBD_CLEAR_SOCK and
NBD_CMD_RECONFIGURE:
nbd_genl_connect // conf_ref=2 (connect and recv_work A)
nbd_open // conf_ref=3
recv_work A done // conf_ref=2
NBD_CLEAR_SOCK // conf_ref=1
nbd_genl_reconfigure // conf_ref=2 (trigger recv_work B)
close nbd // conf_ref=1
recv_work B
config_put // conf_ref=0
atomic_dec(&config->recv_threads); -> UAF
Or only running NBD_CLEAR_SOCK:
nbd_genl_connect // conf_ref=2
nbd_open // conf_ref=3
NBD_CLEAR_SOCK // conf_ref=2
close nbd
nbd_release
config_put // conf_ref=1
recv_work
config_put // conf_ref=0
atomic_dec(&config->recv_threads);
Wiz
CVE-2025-71072 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71072 [MEDIUM] CVE-2025-71072 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71072 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
shmem: fix recovery on rename failures
maple_tree insertions can fail if we are seriously short on memory;
simple_offset_rename() does not recover well if it runs into that.
The same goes for simple_offset_rename_exchange().
Moreover, shmem_whiteout() expects that if it succeeds, the caller will
progress to d_move(), i.e. that shmem_rename2() won't fail past the
successful call of shmem_whiteout().
Not hard to fix, fortunately - mtree_store() can't fail if the index we
are trying to store into is already present in the tree as a singleton.
For simple_offset_rename_exchange() that's enough - we just need to be
careful about the order of operations
Wiz
CVE-2026-23289 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23289 CVE-2026-23289 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23289 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq()
Fix a user triggerable leak on the system call failure path.
Source : NVD
## 7.1
Score
Published March 25, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-firmware
kernel-rt-debug
Sources
NVD
CBL-Mariner 3.0 Severity HIGH Has Fix Added at: Apr 02, 2026
Debian 11, 12, 13 No Fix Added at: Mar 26, 2026
Debian 14 Has Fix
Wiz
CVE-2026-23331 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23331 CVE-2026-23331 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23331 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udp: Unhash auto-bound connected sk from 4-tuple hash table when disconnected.
Let's say we bind() an UDP socket to the wildcard address with a
non-zero port, connect() it to an address, and disconnect it from
the address.
bind() sets SOCK_BINDPORT_LOCK on sk->sk_userlocks (but not
SOCK_BINDADDR_LOCK), and connect() calls udp_lib_hash4() to put
the socket into the 4-tuple hash table.
Then, __udp_disconnect() calls sk->sk_prot->rehash(sk).
It computes a new hash based on the wildcard address and moves
the socket to a new slot in the 4-tuple hash table, leaving a
garbage in the chain that no packet hits.
Let's remove such a socket from 4-tuple has
Wiz
CVE-2023-53851 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53851 CVE-2023-53851 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53851 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/dp: Drop aux devices together with DP controller
Using devres to depopulate the aux bus made sure that upon a probe
deferral the EDP panel device would be destroyed and recreated upon next
attempt.
But the struct device which the devres is tied to is the DPUs
(drm_dev->dev), which may be happen after the DP controller is torn
down.
Indications of this can be seen in the commonly seen EDID-hexdump full
of zeros in the log, or the occasional/rare KASAN fault where the
panel's attempt to read the EDID information causes a use after free on
DP resources.
It's tempting to move the devres to the DP controller's struct device,
but the resources
Wiz
CVE-2026-23061 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23061 [MEDIUM] CVE-2026-23061 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23061 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: kvaser_usb: kvaser_usb_read_bulk_callback(): fix URB memory leak
Fix similar memory leak as in commit 7352e1d5932a ("can: gs_usb:
gs_usb_receive_bulk_callback(): fix URB memory leak").
In kvaser_usb_set_{,data_}bittiming() -> kvaser_usb_setup_rx_urbs(), the
URBs for USB-in transfers are allocated, added to the dev->rx_submitted
anchor and submitted. In the complete callback
kvaser_usb_read_bulk_callback(), the URBs are processed and resubmitted. In
kvaser_usb_remove_interfaces() the URBs are freed by calling
usb_kill_anchored_urbs(&dev->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the
Wiz
CVE-2025-68251 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68251 CVE-2025-68251 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68251 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: avoid infinite loops due to corrupted subpage compact indexes
Robert reported an infinite loop observed by two crafted images.
clusterofs
lclustersize
lclusters
blocksize = lclustersize = 512 lcn = 6 clusterofs = 515
z_erofs_load_lcluster_from_disk()
m->type >= Z_EROFS_LCLUSTER_TYPE_MAX
z_erofs_load_{compact,full}_lcluster()
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and l
Wiz
CVE-2023-54003 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54003 CVE-2023-54003 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54003 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/core: Fix GID entry ref leak when create_ah fails
If AH create request fails, release sgid_attr to avoid GID entry
referrence leak reported while releasing GID table
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-modules-partner
kernel-abi-whitelists
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 202
Wiz
CVE-2026-23142 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23142 [MEDIUM] CVE-2026-23142 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23142 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/damon/sysfs-scheme: cleanup access_pattern subdirs on scheme dir setup failure
When a DAMOS-scheme DAMON sysfs directory setup fails after setup of
access_pattern/ directory, subdirectories of access_pattern/ directory are
not cleaned up. As a result, DAMON sysfs interface is nearly broken until
the system reboots, and the memory for the unremoved directory is leaked.
Cleanup the directories under such failures.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date
Wiz
CVE-2023-54131 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54131 CVE-2023-54131 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54131 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rt2x00: Fix memory leak when handling surveys
When removing a rt2x00 device, its associated channel surveys
are not freed, causing a memory leak observable with kmemleak:
unreferenced object 0xffff9620f0881a00 (size 512):
comm "systemd-udevd", pid 2290, jiffies 4294906974 (age 33.768s)
hex dump (first 32 bytes):
70 44 12 00 00 00 00 00 92 8a 00 00 00 00 00 00 pD..............
00 00 00 00 00 00 00 00 ab 87 01 00 00 00 00 00 ................
backtrace:
[ ] __kmalloc+0x4b/0x130
[ ] rt2800_probe_hw+0xc2b/0x1380 [rt2800lib]
[ ] rt2800usb_probe_hw+0xe/0x60 [rt2800usb]
[ ] rt2x00lib_probe_dev+0x21a/0x7d0 [rt2x00lib]
[ ] rt2x00usb_probe+0x1be/0x980 [
Wiz
CVE-2026-23333 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23333 CVE-2026-23333 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23333 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_set_rbtree: validate open interval overlap
Open intervals do not have an end element, in particular an open
interval at the end of the set is hard to validate because of it is
lacking the end element, and interval validation relies on such end
element to perform the checks.
This patch adds a new flag field to struct nft_set_elem, this is not an
issue because this is a temporary object that is allocated in the stack
from the insert/deactivate path. This flag field is used to specify that
this is the last element in this add/delete command.
The last flag is used, in combination with the start element cookie, to
check if there is a par
Wiz
CVE-2023-54125 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54125 CVE-2023-54125 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54125 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Return error for inconsistent extended attributes
ntfs_read_ea is called when we want to read extended attributes. There
are some sanity checks for the validity of the EAs. However, it fails to
return a proper error code for the inconsistent attributes, which might
lead to unpredicted memory accesses after return.
[ 138.916927] BUG: KASAN: use-after-free in ntfs_set_ea+0x453/0xbf0
[ 138.923876] Write of size 4 at addr ffff88800205cfac by task poc/199
[ 138.931132]
[ 138.933016] CPU: 0 PID: 199 Comm: poc Not tainted 6.2.0-rc1+ #4
[ 138.938070] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.q
Wiz
CVE-2025-68791 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68791 CVE-2025-68791 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68791 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fuse: missing copy_finish in fuse-over-io-uring argument copies
Fix a possible reference count leak of payload pages during
fuse argument copies.
[Joanne: simplified error cleanup]
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-devel
kernel-firmware
Sources
NVD
Debian 14 Has Fix Added at: Jan 14, 2026
Red Hat 6 Severity LOW No Fix Added at: Jan 18, 2026
Ubuntu 16
Wiz
CVE-2023-54233 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54233 CVE-2023-54233 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54233 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: SOF: avoid a NULL dereference with unsupported widgets
If an IPC4 topology contains an unsupported widget, its .module_info
field won't be set, then sof_ipc4_route_setup() will cause a kernel
Oops trying to dereference it. Add a check for such cases.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-cross-headers
rv
Sources
NVD
Debian 11, 12 No Fix Added at: Dec
Wiz
CVE-2023-54069 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54069 CVE-2023-54069 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54069 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix BUG in ext4_mb_new_inode_pa() due to overflow
When we calculate the end position of ext4_free_extent, this position may
be exactly where ext4_lblk_t (i.e. uint) overflows. For example, if
ac_g_ex.fe_logical is 4294965248 and ac_orig_goal_len is 2048, then the
computed end is 0x100000000, which is 0. If ac->ac_o_ex.fe_logical is not
the first case of adjusting the best extent, that is, new_bex_end > 0, the
following BUG_ON will be triggered:
kernel BUG at fs/ext4/mballoc.c:5116!
invalid opcode: 0000 [#1] PREEMPT SMP PTI
CPU: 3 PID: 673 Comm: xfs_io Tainted: G E 6.5.0-rc1+ #279
RIP: 0010:ext4_mb_new_inode_pa+0xc5/0x430
Call Trace: ext4_mb_u
Wiz
CVE-2025-68753 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68753 CVE-2025-68753 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68753 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: firewire-motu: add bounds check in put_user loop for DSP events
In the DSP event handling code, a put_user() loop copies event data.
When the user buffer size is not aligned to 4 bytes, it could overwrite
beyond the buffer boundary.
Fix by adding a bounds check before put_user().
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-debug-vdso
kernel-rt-debug-modules-e
Wiz
CVE-2022-50731 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50731 CVE-2022-50731 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50731 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: akcipher - default implementation for setting a private key
Changes from v1:
removed the default implementation from set_pub_key: it is assumed that
an implementation must always have this callback defined as there are
no use case for an algorithm, which doesn't need a public key
Many akcipher implementations (like ECDSA) support only signature
verifications, so they don't have all callbacks defined.
Commit 78a0324f4a53 ("crypto: akcipher - default implementations for
request callbacks") introduced default callbacks for sign/verify
operations, which just return an error code.
However, these are not enough, because before calling sign the ca
Wiz
CVE-2026-23207 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23207 [MEDIUM] CVE-2026-23207 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23207 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: tegra210-quad: Protect curr_xfer check in IRQ handler
Now that all other accesses to curr_xfer are done under the lock,
protect the curr_xfer NULL check in tegra_qspi_isr_thread() with the
spinlock. Without this protection, the following race can occur:
CPU0 (ISR thread) CPU1 (timeout path)
if (!tqspi->curr_xfer)
// sees non-NULL
spin_lock()
tqspi->curr_xfer = NULL
spin_unlock()
handle_*_xfer()
spin_lock()
t = tqspi->curr_xfer // NULL!
... t->len ... // NULL dereference!
With this patch, all curr_xfer accesses are now properly synchronized.
Although all accesses to curr_xfer are done under the lock, in
tegra_qspi_isr_thread() it checks for
Wiz
CVE-2025-40345 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40345 CVE-2025-40345 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40345 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: storage: sddr55: Reject out-of-bound new_pba
Discovered by Atuin - Automated Vulnerability Discovery Engine.
new_pba comes from the status packet returned after each write.
A bogus device could report values beyond the block count derived
from info->capacity, letting the driver walk off the end of
pba_to_lba[] and corrupt heap memory.
Reject PBAs that exceed the computed block count and fail the
transfer so we avoid touching out-of-range mapping entries.
Source : NVD
## 6.7
Score
Published December 12, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
Wiz
CVE-2023-54115 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54115 CVE-2023-54115 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54115 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pcmcia: rsrc_nonstatic: Fix memory leak in nonstatic_release_resource_db()
When nonstatic_release_resource_db() frees all resources associated
with an PCMCIA socket, it forgets to free socket_data too, causing
a memory leak observable with kmemleak:
unreferenced object 0xc28d1000 (size 64):
comm "systemd-udevd", pid 297, jiffies 4294898478 (age 194.484s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 f0 85 0e c3 00 00 00 00 ................
00 00 00 00 0c 10 8d c2 00 00 00 00 00 00 00 00 ................
backtrace:
[ ] __kmem_cache_alloc_node+0x2d7/0x4a0
[] kmalloc_trace+0x31/0xa4
[ ] nonstatic_init+0x24/0x1a4 [pcmcia_rsrc]
[ ] pcmcia_register_
Wiz
CVE-2026-23168 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23168 [MEDIUM] CVE-2026-23168 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23168 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
flex_proportions: make fprop_new_period() hardirq safe
Bernd has reported a lockdep splat from flexible proportions code that is
essentially complaining about the following race:
...
blk_mq_end_request()
blk_update_request()
ext4_end_bio()
folio_end_writeback()
__wb_writeout_add()
__fprop_add_percpu_max()
if (unlikely(max_frac sequence);
- sees odd sequence so loops indefinitely
Note that a deadlock like this is only possible if the bdi has configured
maximum fraction of writeout throughput which is very rare in general but
frequent for example for FUSE bdis. To fix this problem we have to make
sure write section of the sequence counter is irqsaf
Wiz
CVE-2022-50767 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50767 CVE-2022-50767 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50767 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fbdev: smscufx: Fix several use-after-free bugs
Several types of UAFs can occur when physically removing a USB device.
Adds ufx_ops_destroy() function to .fb_destroy of fb_ops, and
in this function, there is kref_put() that finally calls ufx_free().
This fix prevents multiple UAFs.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt
linux-ibm-5.4
Sources
NVD
Debia
Wiz
CVE-2023-54258 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54258 CVE-2023-54258 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54258 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: fix potential oops in cifs_oplock_break
With deferred close we can have closes that race with lease breaks,
and so with the current checks for whether to send the lease response,
oplock_response(), this can mean that an unmount (kill_sb) can occur
just before we were checking if the tcon->ses is valid. See below:
[Fri Aug 4 04:12:50 2023] RIP: 0010:cifs_oplock_break+0x1f7/0x5b0 [cifs]
[Fri Aug 4 04:12:50 2023] Code: 7d a8 48 8b 7d c0 c0 e9 02 48 89 45 b8 41 89 cf e8 3e f5 ff ff 4c 89 f7 41 83 e7 01 e8 82 b3 03 f2 49 8b 45 50 48 85 c0 74 5e 83 78 60 00 74 57 45 84 ff 75 52 48 8b 43 98 48 83 eb 68 48 39
[Fri Aug 4 04:12:50 2023] RSP: 0018:ffffb
Wiz
CVE-2025-68353 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68353 CVE-2025-68353 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68353 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: vxlan: prevent NULL deref in vxlan_xmit_one
Neither sock4 nor sock6 pointers are guaranteed to be non-NULL in
vxlan_xmit_one, e.g. if the iface is brought down. This can lead to the
following NULL dereference:
BUG: kernel NULL pointer dereference, address: 0000000000000010
Oops: Oops: 0000 [#1] SMP NOPTI
RIP: 0010:vxlan_xmit_one+0xbb3/0x1580
Call Trace:
vxlan_xmit+0x429/0x610
dev_hard_start_xmit+0x55/0xa0
__dev_queue_xmit+0x6d0/0x7f0
ip_finish_output2+0x24b/0x590
ip_output+0x63/0x110
Mentioned commits changed the code path in vxlan_xmit_one and as a side
effect the sock4/6 pointer validity checks in vxlan(6)_get_route were
lost. Fix this by a
Wiz
CVE-2025-71106 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71106 [MEDIUM] CVE-2025-71106 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71106 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: PM: Fix reverse check in filesystems_freeze_callback()
The freeze_all_ptr check in filesystems_freeze_callback() introduced by
commit a3f8f8662771 ("power: always freeze efivarfs") is reverse which
quite confusingly causes all file systems to be frozen when
filesystem_freeze_enabled is false.
On my systems it causes the WARN_ON_ONCE() in __set_task_frozen() to
trigger, most likely due to an attempt to freeze a file system that is
not ready for that.
Add a logical negation to the check in question to reverse it as
appropriate.
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linu
Wiz
CVE-2022-50855 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50855 CVE-2022-50855 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50855 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: prevent leak of lsm program after failed attach
In [0], we added the ability to bpf_prog_attach LSM programs to cgroups,
but in our validation to make sure the prog is meant to be attached to
BPF_LSM_CGROUP, we return too early if the check fails. This results in
lack of decrementing prog's refcnt (through bpf_prog_put)
leaving the LSM program alive past the point of the expected lifecycle.
This fix allows for the decrement to take place.
[0] https://lore.kernel.org/all/[email protected]/
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Ha
Wiz
CVE-2023-54172 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54172 CVE-2023-54172 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54172 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/hyperv: Disable IBT when hypercall page lacks ENDBR instruction
On hardware that supports Indirect Branch Tracking (IBT), Hyper-V VMs
with ConfigVersion 9.3 or later support IBT in the guest. However,
current versions of Hyper-V have a bug in that there's not an ENDBR64
instruction at the beginning of the hypercall page. Since hypercalls are
made with an indirect call to the hypercall page, all hypercall attempts
fail with an exception and Linux panics.
A Hyper-V fix is in progress to add ENDBR64. But guard against the Linux
panic by clearing X86_FEATURE_IBT if the hypercall page doesn't start
with ENDBR. The VM will boot and run without IBT.
Wiz
CVE-2025-68795 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68795 CVE-2025-68795 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68795 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ethtool: Avoid overflowing userspace buffer on stats query
The ethtool -S command operates across three ioctl calls:
ETHTOOL_GSSET_INFO for the size, ETHTOOL_GSTRINGS for the names, and
ETHTOOL_GSTATS for the values.
If the number of stats changes between these calls (e.g., due to device
reconfiguration), userspace's buffer allocation will be incorrect,
potentially leading to buffer overflow.
Drivers are generally expected to maintain stable stat counts, but some
drivers (e.g., mlx5, bnx2x, bna, ksz884x) use dynamic counters, making
this scenario possible.
Some drivers try to handle this internally:
bnad_get_ethtool_stats() returns early in case
Wiz
CVE-2023-53824 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53824 CVE-2023-53824 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53824 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netlink: annotate lockless accesses to nlk->max_recvmsg_len
syzbot reported a data-race in data-race in netlink_recvmsg() [1]
Indeed, netlink_recvmsg() can be run concurrently,
and netlink_dump() also needs protection.
[1]
BUG: KCSAN: data-race in netlink_recvmsg / netlink_recvmsg
read to 0xffff888141840b38 of 8 bytes by task 23057 on cpu 0:
netlink_recvmsg+0xea/0x730 net/netlink/af_netlink.c:1988
sock_recvmsg_nosec net/socket.c:1017 [inline]
sock_recvmsg net/socket.c:1038 [inline]
__sys_recvfrom+0x1ee/0x2e0 net/socket.c:2194
__do_sys_recvfrom net/socket.c:2212 [inline]
__se_sys_recvfrom net/socket.c:2208 [inline]
__x64_sys_recvfrom+0x78/0x90 net
Wiz
CVE-2026-23098 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.8
CVE-2026-23098 [HIGH] CVE-2026-23098 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23098 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netrom: fix double-free in nr_route_frame()
In nr_route_frame(), old_skb is immediately freed without checking if
nr_neigh->ax25 pointer is NULL. Therefore, if nr_neigh->ax25 is NULL,
the caller function will free old_skb again, causing a double-free bug.
Therefore, to prevent this, we need to modify it to check whether
nr_neigh->ax25 is NULL before freeing old_skb.
Source : NVD
## 7.8
Score
Published February 4, 2026
Severity HIGH
CNA Score 8.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.5
E
Wiz
CVE-2026-23024 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23024 [MEDIUM] CVE-2026-23024 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23024 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix memory leak of flow steer list on rmmod
The flow steering list maintains entries that are added and removed as
ethtool creates and deletes flow steering rules. Module removal with active
entries causes memory leak as the list is not properly cleaned up.
Prevent this by iterating through the remaining entries in the list and
freeing the associated memory during module removal. Add a spinlock
(flow_steer_list_lock) to protect the list access from multiple threads.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV
Wiz
CVE-2026-23001 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23001 [HIGH] CVE-2026-23001 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23001 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
macvlan: fix possible UAF in macvlan_forward_source()
Add RCU protection on (struct macvlan_source_entry)->vlan.
Whenever macvlan_hash_del_source() is called, we must clear
entry->vlan pointer before RCU grace period starts.
This allows macvlan_forward_source() to skip over
entries queued for freeing.
Note that macvlan_dev are already RCU protected, as they
are embedded in a standard netdev (netdev_priv(ndev)).
https: //lore.kernel.org/netdev/[email protected]/T/#u
Source : NVD
## 7.8
Score
Published January 25, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Rocky Linux
Has Public Explo
Wiz
CVE-2023-54145 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54145 CVE-2023-54145 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54145 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: drop unnecessary user-triggerable WARN_ONCE in verifierl log
It's trivial for user to trigger "verifier log line truncated" warning,
as verifier has a fixed-sized buffer of 1024 bytes (as of now), and there are at
least two pieces of user-provided information that can be output through
this buffer, and both can be arbitrarily sized by user:
BTF names;
BTF.ext source code lines strings.
Verifier log buffer should be properly sized for typical verifier state
output. But it's sort-of expected that this buffer won't be long enough
in some circumstances. So let's drop the check. In any case code will
work correctly, at worst truncating a part of a
Wiz
CVE-2023-54083 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54083 CVE-2023-54083 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54083 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
phy: tegra: xusb: Clear the driver reference in usb-phy dev
For the dual-role port, it will assign the phy dev to usb-phy dev and
use the port dev driver as the dev driver of usb-phy.
When we try to destroy the port dev, it will destroy its dev driver
as well. But we did not remove the reference from usb-phy dev. This
might cause the use-after-free issue in KASAN.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N
Wiz
CVE-2026-23124 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23124 [MEDIUM] CVE-2026-23124 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23124 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: annotate data-race in ndisc_router_discovery()
syzbot found that ndisc_router_discovery() could read and write
in6_dev->ra_mtu without holding a lock [1]
This looks fine, IFLA_INET6_RA_MTU is best effort.
Add READ_ONCE()/WRITE_ONCE() to document the race.
Note that we might also reject illegal MTU values
(mtu skb->dev->mtu) in a future patch.
[1]
BUG: KCSAN: data-race in ndisc_router_discovery / ndisc_router_discovery
read to 0xffff888119809c20 of 4 bytes by task 25817 on cpu 1:
ndisc_router_discovery+0x151d/0x1c90 net/ipv6/ndisc.c:1558
ndisc_rcv+0x2ad/0x3d0 net/ipv6/ndisc.c:1841
icmpv6_rcv+0xe5a/0x12f0 net/ipv6/icmp.c:989
ip6_protocol_de
Wiz
CVE-2025-71089 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71089 [HIGH] CVE-2025-71089 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71089 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommu: disable SVA when CONFIG_X86 is set
Patch series "Fix stale IOTLB entries for kernel address space", v7.
This proposes a fix for a security vulnerability related to IOMMU Shared
Virtual Addressing (SVA). In an SVA context, an IOMMU can cache kernel
page table entries. When a kernel page table page is freed and
reallocated for another purpose, the IOMMU might still hold stale,
incorrect entries. This can be exploited to cause a use-after-free or
write-after-free condition, potentially leading to privilege escalation or
data corruption.
This solution introduces a deferred freeing mechanism for kernel page
table pages, which provides a safe win
Wiz
CVE-2026-23133 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23133 [MEDIUM] CVE-2026-23133 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23133 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath10k: fix dma_free_coherent() pointer
dma_alloc_coherent() allocates a DMA mapped buffer and stores the
addresses in XXX_unaligned fields. Those should be reused when freeing
the buffer rather than the aligned addresses.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-oem-6.14
linux-realtime
Sources
NVD
CBL-Mariner 3.0 Severit
Wiz
CVE-2026-23065 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23065 [MEDIUM] CVE-2026-23065 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23065 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86/amd: Fix memory leak in wbrf_record()
The tmp buffer is allocated using kcalloc() but is not freed if
acpi_evaluate_dsm() fails. This causes a memory leak in the error path.
Fix this by explicitly freeing the tmp buffer in the error handling
path of acpi_evaluate_dsm().
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-apm
kern
Wiz
CVE-2023-54033 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54033 CVE-2023-54033 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54033 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: fix a memory leak in the LRU and LRU_PERCPU hash maps
The LRU and LRU_PERCPU maps allocate a new element on update before locking the
target hash table bucket. Right after that the maps try to lock the bucket.
If this fails, then maps return -EBUSY to the caller without releasing the
allocated element. This makes the element untracked: it doesn't belong to
either of free lists, and it doesn't belong to the hash table, so can't be
re-used; this eventually leads to the permanent -ENOMEM on LRU map updates,
which is unexpected. Fix this by returning the element to the local free list
if bucket locking fails.
Source : NVD
Published December 24, 2
Wiz
CVE-2026-31411 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31411 CVE-2026-31411 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31411 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: atm: fix crash due to unvalidated vcc pointer in sigd_send()
Reproducer available at 1 .
The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc
pointer from msg->vcc and uses it directly without any validation. This
pointer comes from userspace via sendmsg() and can be arbitrarily forged:
int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0);
ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon
struct msghdr msg = { .msg_iov = &iov, ... };
*(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer
sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef
In normal operation, the kernel sends the vcc pointer to the signaling
daemon via
Wiz
CVE-2025-71064 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71064 CVE-2025-71064 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71064 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: hns3: using the num_tqps in the vf driver to apply for resources
Currently, hdev->htqp is allocated using hdev->num_tqps, and kinfo->tqp
is allocated using kinfo->num_tqps. However, kinfo->num_tqps is set to
min(new_tqps, hdev->num_tqps); Therefore, kinfo->num_tqps may be smaller
than hdev->num_tqps, which causes some hdev->htqp[i] to remain
uninitialized in hclgevf_knic_setup().
Thus, this patch allocates hdev->htqp and kinfo->tqp using hdev->num_tqps,
ensuring that the lengths of hdev->htqp and kinfo->tqp are consistent
and that all elements are properly initialized.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technolo
Wiz
CVE-2025-68764 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68764 CVE-2025-68764 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68764 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFS: Automounted filesystems should inherit ro,noexec,nodev,sync flags
When a filesystem is being automounted, it needs to preserve the
user-set superblock mount options, such as the "ro" flag.
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
gfs2-kmp-64kb
kernel-syms
Sources
NVD
CBL-Mariner 3.0 Severity MEDIUM Has Fix Added at: Feb 12, 2026
Container-Optimized OS Has Fix Ad
Wiz
CVE-2023-54021 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54021 CVE-2023-54021 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54021 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: set goal start correctly in ext4_mb_normalize_request
We need to set ac_g_ex to notify the goal start used in
ext4_mb_find_by_goal. Set ac_g_ex instead of ac_f_ex in
ext4_mb_normalize_request.
Besides we should assure goal start is in range [first_data_block,
blocks_count) as ext4_mb_initialize_context does.
[ Added a check to make sure size is less than ar->pright; otherwise
we could end up passing an underflowed value of ar->pright - size to
ext4_get_group_no_and_offset(), which will trigger a BUG_ON later on.
TYT ]
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Expl
Wiz
CVE-2026-23176 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23176 CVE-2026-23176 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23176 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: toshiba_haps: Fix memory leaks in add/remove routines
toshiba_haps_add() leaks the haps object allocated by it if it returns
an error after allocating that object successfully.
toshiba_haps_remove() does not free the object pointed to by
toshiba_haps before clearing that pointer, so it becomes unreachable
allocated memory.
Address these memory leaks by using devm_kzalloc() for allocating
the memory in question.
Source : NVD
Published February 14, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Proba
Wiz
CVE-2023-54164 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54164 CVE-2023-54164 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54164 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: ISO: fix iso_conn related locking and validity issues
sk->sk_state indicates whether iso_pi(sk)->conn is valid. Operations
that check/update sk_state and access conn should hold lock_sock,
otherwise they can race.
The order of taking locks is hci_dev_lock > lock_sock > iso_conn_lock,
which is how it is in connect/disconnect_cfm -> iso_conn_del ->
iso_chan_del.
Fix locking in iso_connect_cis/bis and sendmsg/recvmsg to take lock_sock
around updating sk_state and conn.
iso_conn_del must not occur during iso_connect_cis/bis, as it frees the
iso_conn. Hold hdev->lock longer to prevent that.
This should not reintroduce the issue fixed in co
Wiz
CVE-2025-68253 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68253 CVE-2025-68253 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68253 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm: don't spin in add_stack_record when gfp flags don't allow
syzbot was able to find the following path:
add_stack_record_to_list mm/page_owner.c:182 [inline]
inc_stack_record_count mm/page_owner.c:214 [inline]
__set_page_owner+0x2c3/0x4a0 mm/page_owner.c:333
set_page_owner include/linux/page_owner.h:32 [inline]
post_alloc_hook+0x240/0x2a0 mm/page_alloc.c:1851
prep_new_page mm/page_alloc.c:1859 [inline]
get_page_from_freelist+0x21e4/0x22c0 mm/page_alloc.c:3858
alloc_pages_nolock_noprof+0x94/0x120 mm/page_alloc.c:7554
Don't spin in add_stack_record_to_list() when it is called
from *_nolock() context.
Source : NVD
Published December 16, 2025
CNA
Wiz
CVE-2025-68293 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68293 CVE-2025-68293 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68293 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/huge_memory: fix NULL pointer deference when splitting folio
Commit c010d47f107f ("mm: thp: split huge page to any lower order pages")
introduced an early check on the folio's order via mapping->flags before
proceeding with the split work.
This check introduced a bug: for shmem folios in the swap cache and
truncated folios, the mapping pointer can be NULL. Accessing
mapping->flags in this state leads directly to a NULL pointer dereference.
This commit fixes the issue by moving the check for mapping != NULL before
any attempt to access mapping->flags.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Wiz
CVE-2023-54080 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54080 CVE-2023-54080 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54080 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: zoned: skip splitting and logical rewriting on pre-alloc write
When doing a relocation, there is a chance that at the time of
btrfs_reloc_clone_csums(), there is no checksum for the corresponding
region.
In this case, btrfs_finish_ordered_zoned()'s sum points to an invalid item
and so ordered_extent's logical is set to some invalid value. Then,
btrfs_lookup_block_group() in btrfs_zone_finish_endio() failed to find a
block group and will hit an assert or a null pointer dereference as
following.
This can be reprodcued by running btrfs/028 several times (e.g, 4 to 16
times) with a null_blk setup. The device's zone size and capacity is set to
3
Wiz
CVE-2025-68258 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68258 CVE-2025-68258 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68258 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
comedi: multiq3: sanitize config options in multiq3_attach()
Syzbot identified an issue [1] in multiq3_attach() that induces a
task timeout due to open() or COMEDI_DEVCONFIG ioctl operations,
specifically, in the case of multiq3 driver.
This problem arose when syzkaller managed to craft weird configuration
options used to specify the number of channels in encoder subdevice.
If a particularly great number is passed to s->n_chan in
multiq3_attach() via it->options[2], then multiple calls to
multiq3_encoder_reset() at the end of driver-specific attach() method
will be running for minutes, thus blocking tasks and affected devices
as well.
While this i
Wiz
CVE-2026-23201 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23201 [MEDIUM] CVE-2026-23201 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23201 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ceph: fix oops due to invalid pointer for kfree() in parse_longname()
ls /mnt/my_ceph/.snap
The variable str is guarded by __free(kfree), but advanced by one for
skipping the initial '_' in snapshot names. Thus, kfree() is called
with an invalid pointer. This patch removes the need for advancing the
pointer so kfree() is called with correct memory pointer.
Steps to reproduce:
Create snapshots on a cephfs volume (I've 63 snaps in my testcase)
Add cephfs mount to fstab
$ echo "[email protected]=/volumes/datapool/stuff/3461082b-ecc9-4e82-8549-3fd2590d3fb6 /mnt/test/stuff ceph acl,noatime,_netdev 0 0" >> /etc/fstab
Reboot the system$ systemc
Wiz
CVE-2023-54276 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54276 CVE-2023-54276 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54276 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: move init of percpu reply_cache_stats counters back to nfsd_init_net
Commit f5f9d4a314da ("nfsd: move reply cache initialization into nfsd
startup") moved the initialization of the reply cache into nfsd startup,
but didn't account for the stats counters, which can be accessed before
nfsd is ever started. The result can be a NULL pointer dereference when
someone accesses /proc/fs/nfsd/reply_cache_stats while nfsd is still
shut down.
This is a regression and a user-triggerable oops in the right situation:
non-x86_64 arch
/proc/fs/nfsd is mounted in the namespace
nfsd is not started in the namespace
unprivileged user calls "cat /proc/fs/nfsd
Wiz
CVE-2025-71126 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71126 [MEDIUM] CVE-2025-71126 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71126 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: avoid deadlock on fallback while reinjecting
Jakub reported an MPTCP deadlock at fallback time:
## WARNING: possible recursive locking detected
6.18.0-rc7-virtme #1 Not tainted
mptcp_connect/20858 is trying to acquire lock:
ff1100001da18b60 (&msk->fallback_lock){+.-.}-{3:3}, at: __mptcp_try_fallback+0xd8/0x280
but task is already holding lock:
ff1100001da18b60 (&msk->fallback_lock){+.-.}-{3:3}, at: __mptcp_retrans+0x352/0xaa0
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&msk->fallback_lock);
lock(&msk->fallback_lock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks
Wiz
CVE-2023-54084 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54084 CVE-2023-54084 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54084 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: firewire-digi00x: prevent potential use after free
This code was supposed to return an error code if init_stream()
failed, but it instead freed dg00x->rx_stream and returned success.
This potentially leads to a use after free.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-oracle
kernel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Ha
Wiz
CVE-2025-68334 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68334 CVE-2025-68334 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68334 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86/amd/pmc: Add support for Van Gogh SoC
The ROG Xbox Ally (non-X) SoC features a similar architecture to the
Steam Deck. While the Steam Deck supports S3 (s2idle causes a crash),
this support was dropped by the Xbox Ally which only S0ix suspend.
Since the handler is missing here, this causes the device to not suspend
and the AMD GPU driver to crash while trying to resume afterwards due to
a power hang.
Source : NVD
## 5.5
Score
Published December 22, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Wiz
CVE-2025-71108 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71108 [MEDIUM] CVE-2025-71108 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71108 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: typec: ucsi: Handle incorrect num_connectors capability
The UCSI spec states that the num_connectors field is 7 bits, and the
8th bit is reserved and should be set to zero.
Some buggy FW has been known to set this bit, and it can lead to a
system not booting.
Flag that the FW is not behaving correctly, and auto-fix the value
so that the system boots correctly.
Found on Lenovo P1 G8 during Linux enablement program. The FW will
be fixed, but seemed worth addressing in case it hit platforms that
aren't officially Linux supported.
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Lin
Wiz
CVE-2025-68211 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68211 [MEDIUM] CVE-2025-68211 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68211 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksm: use range-walk function to jump over holes in scan_get_next_rmap_item
Currently, scan_get_next_rmap_item() walks every page address in a VMA to
locate mergeable pages. This becomes highly inefficient when scanning
large virtual memory areas that contain mostly unmapped regions, causing
ksmd to use large amount of cpu without deduplicating much pages.
This patch replaces the per-address lookup with a range walk using
walk_page_range(). The range walker allows KSM to skip over entire
unmapped holes in a VMA, avoiding unnecessary lookups. This problem was
previously discussed in [1].
Consider the following test program which creates a 32 TiB map
Wiz
CVE-2026-23261 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23261 CVE-2026-23261 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23261 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-fc: release admin tagset if init fails
nvme_fabrics creates an NVMe/FC controller in following path:
nvmf_dev_write()
-> nvmf_create_ctrl()
-> nvme_fc_create_ctrl()
-> nvme_fc_init_ctrl()
nvme_fc_init_ctrl() allocates the admin blk-mq resources right after
nvme_add_ctrl() succeeds. If any of the subsequent steps fail (changing
the controller state, scheduling connect work, etc.), we jump to the
fail_ctrl path, which tears down the controller references but never
frees the admin queue/tag set. The leaked blk-mq allocations match the
kmemleak report seen during blktests nvme/fc.
Check ctrl->ctrl.admin_tagset in the fail_ctrl path and call
nvme
Wiz
CVE-2025-68751 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68751 CVE-2025-68751 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68751 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/fpu: Fix false-positive kmsan report in fpu_vstl()
A false-positive kmsan report is detected when running ping command.
An inline assembly instruction 'vstl' can write varied amount of bytes
depending on value of 'index' argument. If 'index' > 0, 'vstl' writes
at least 2 bytes.
clang generates kmsan write helper call depending on inline assembly
constraints. Constraints are evaluated compile-time, but value of
'index' argument is known only at runtime.
clang currently generates call to __msan_instrument_asm_store with 1 byte
as size. Manually call kmsan function to indicate correct amount of bytes
written and fix false-positive report.
This
Wiz
CVE-2026-23014 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23014 [MEDIUM] CVE-2026-23014 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23014 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf: Ensure swevent hrtimer is properly destroyed
With the change to hrtimer_try_to_cancel() in
perf_swevent_cancel_hrtimer() it appears possible for the hrtimer to
still be active by the time the event gets freed.
Make sure the event does a full hrtimer_cancel() on the free path by
installing a perf_event::destroy handler.
Source : NVD
## 5.5
Score
Published January 28, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.1
Exploitation Probability (EPSS) N/A
Aff
Wiz
CVE-2023-54197 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54197 CVE-2023-54197 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54197 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Revert "Bluetooth: btsdio: fix use after free bug in btsdio_remove due to unfinished work"
This reverts commit 1e9ac114c4428fdb7ff4635b45d4f46017e8916f.
This patch introduces a possible null-ptr-def problem. Revert it. And the
fixed bug by this patch have resolved by commit 73f7b171b7c0 ("Bluetooth:
btsdio: fix use after free bug in btsdio_remove due to race condition").
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability
Wiz
CVE-2026-23032 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23032 CVE-2026-23032 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23032 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
null_blk: fix kmemleak by releasing references to fault configfs items
When CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION is enabled, the null-blk
driver sets up fault injection support by creating the timeout_inject,
requeue_inject, and init_hctx_fault_inject configfs items as children
of the top-level nullbX configfs group.
However, when the nullbX device is removed, the references taken to
these fault-config configfs items are not released. As a result,
kmemleak reports a memory leak, for example:
unreferenced object 0xc00000021ff25c40 (size 32):
comm "mkdir", pid 10665, jiffies 4322121578
hex dump (first 32 bytes):
69 6e 69 74 5f 68 63 74 78 5f 66 6
Wiz
CVE-2023-54136 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54136 CVE-2023-54136 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54136 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
serial: sprd: Fix DMA buffer leak issue
Release DMA buffer when _probe() returns failure to avoid memory leak.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules-extra
kernel-rt-64k-debug-devel-matched
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 9 Severity MEDIUM Has Fix Added at: Dec 26,
Wiz
CVE-2026-23381 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23381 CVE-2026-23381 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23381 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled
When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. Then, if neigh_suppress is enabled and an ICMPv6
Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will
dereference ipv6_stub->nd_tbl which is NULL, passing it to
neigh_lookup(). This causes a kernel NULL pointer dereference.
BUG: kernel NULL pointer dereference, address: 0000000000000268
Oops: 0000 [#1] PREEMPT SMP NOPTI
[...]
RIP: 0010:neigh_lookup+0x16/0xe0
[...]
Call Trace: ? neigh_lookup+0x16/0xe0
br_do_supp
Wiz
CVE-2026-23164 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23164 [MEDIUM] CVE-2026-23164 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23164 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rocker: fix memory leak in rocker_world_port_post_fini()
In rocker_world_port_pre_init(), rocker_port->wpriv is allocated with
kzalloc(wops->port_priv_size, GFP_KERNEL). However, in
rocker_world_port_post_fini(), the memory is only freed when
wops->port_post_fini callback is set:
if (!wops->port_post_fini)
return;
wops->port_post_fini(rocker_port);
kfree(rocker_port->wpriv);
Since rocker_ofdpa_ops does not implement port_post_fini callback
(it is NULL), the wpriv memory allocated for each port is never freed
when ports are removed. This leads to a memory leak of
sizeof(struct ofdpa_port) bytes per port on every device removal.
Fix this by always
Wiz
CVE-2026-23058 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23058 CVE-2026-23058 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23058 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: ems_usb: ems_usb_read_bulk_callback(): fix URB memory leak
Fix similar memory leak as in commit 7352e1d5932a ("can: gs_usb:
gs_usb_receive_bulk_callback(): fix URB memory leak").
In ems_usb_open(), the URBs for USB-in transfers are allocated, added to
the dev->rx_submitted anchor and submitted. In the complete callback
ems_usb_read_bulk_callback(), the URBs are processed and resubmitted. In
ems_usb_close() the URBs are freed by calling
usb_kill_anchored_urbs(&dev->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the complete function is called. This means that once an
in-URB has been comp
Wiz
CVE-2023-54218 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54218 CVE-2023-54218 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54218 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: Fix load-tearing on sk->sk_stamp in sock_recv_cmsgs().
KCSAN found a data race in sock_recv_cmsgs() where the read access
to sk->sk_stamp needs READ_ONCE().
BUG: KCSAN: data-race in packet_recvmsg / packet_recvmsg
write (marked) to 0xffff88803c81f258 of 8 bytes by task 19171 on cpu 0:
sock_write_timestamp include/net/sock.h:2670 [inline]
sock_recv_cmsgs include/net/sock.h:2722 [inline]
packet_recvmsg+0xb97/0xd00 net/packet/af_packet.c:3489
sock_recvmsg_nosec net/socket.c:1019 [inline]
sock_recvmsg+0x11a/0x130 net/socket.c:1040
sock_read_iter+0x176/0x220 net/socket.c:1118
call_read_iter include/linux/fs.h:1845 [inline]
new_sync_read fs/read_wr
Wiz
CVE-2025-71149 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71149 [MEDIUM] CVE-2025-71149 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71149 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/poll: correctly handle io_poll_add() return value on update
When the core of io_uring was updated to handle completions
consistently and with fixed return codes, the POLL_REMOVE opcode
with updates got slightly broken. If a POLL_ADD is pending and
then POLL_REMOVE is used to update the events of that request, if that
update causes the POLL_ADD to now trigger, then that completion is lost
and a CQE is never posted.
Additionally, ensure that if an update does cause an existing POLL_ADD
to complete, that the completion value isn't always overwritten with
-ECANCELED. For that case, whatever io_poll_add() set the value to
should just be retaine
Wiz
CVE-2026-23270 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23270 [HIGH] CVE-2026-23270 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23270 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and shared blocks
As Paolo said earlier [1]:
"Since the blamed commit below, classify can return TC_ACT_CONSUMED while
the current skb being held by the defragmentation engine. As reported by
GangMin Kim, if such packet is that may cause a UaF when the defrag engine
later on tries to tuch again such packet."
act_ct was never meant to be used in the egress path, however some users
are attaching it to egress today [2]. Attempting to reach a middle
ground, we noticed that, while most qdiscs are not handling
TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we
address the issue
Wiz
CVE-2025-68227 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68227 CVE-2025-68227 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68227 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: Fix proto fallback detection with BPF
The sockmap feature allows bpf syscall from userspace, or based
on bpf sockops, replacing the sk_prot of sockets during protocol stack
processing with sockmap's custom read/write interfaces.
'''
tcp_rcv_state_process()
syn_recv_sock()/subflow_syn_recv_sock()
tcp_init_transfer(BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
bpf_skops_established sk_prot to compare with the native sk_prot, but this
is incorrect when sockmap is used, as we may incorrectly set
sk->sk_socket->ops.
This fix uses the more generic sk_family for the comparison instead.
Additionally, this also prevents a WARNING from occurring:
result from
Wiz
CVE-2023-53842 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53842 CVE-2023-53842 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53842 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: codecs: wcd-mbhc-v2: fix resource leaks on component remove
The MBHC resources must be released on component probe failure and
removal so can not be tied to the lifetime of the component device.
This is specifically needed to allow probe deferrals of the sound card
which otherwise fails when reprobing the codec component:
snd-sc8280xp sound: ASoC: failed to instantiate card -517
genirq: Flags mismatch irq 299. 00002001 (mbhc sw intr) vs. 00002001 (mbhc sw intr)
wcd938x_codec audio-codec: Failed to request mbhc interrupts -16
wcd938x_codec audio-codec: mbhc initialization failed
wcd938x_codec audio-codec: ASoC: error at snd_soc_component_prob
Wiz
CVE-2023-54112 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54112 CVE-2023-54112 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54112 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
kcm: Fix memory leak in error path of kcm_sendmsg()
syzbot reported a memory leak like below:
BUG: memory leak
unreferenced object 0xffff88810b088c00 (size 240):
comm "syz-executor186", pid 5012, jiffies 4294943306 (age 13.680s)
hex dump (first 32 bytes):
00 89 08 0b 81 88 ff ff 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[ ] __alloc_skb+0x1ef/0x230 net/core/skbuff.c:634
[ ] alloc_skb include/linux/skbuff.h:1289 [inline]
[ ] kcm_sendmsg+0x269/0x1050 net/kcm/kcmsock.c:815
[ ] sock_sendmsg_nosec net/socket.c:725 [inline]
[ ] sock_sendmsg+0x56/0xb0 net/socket.c:748
[ ] ____sys_se
Wiz
CVE-2022-50764 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50764 CVE-2022-50764 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50764 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6/sit: use DEV_STATS_INC() to avoid data-races
syzbot/KCSAN reported that multiple cpus are updating dev->stats.tx_error
concurrently.
This is because sit tunnels are NETIF_F_LLTX, meaning their ndo_start_xmit()
is not protected by a spinlock.
While original KCSAN report was about tx path, rx path has the same issue.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-
Wiz
CVE-2023-54174 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54174 CVE-2023-54174 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54174 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vfio: Fix NULL pointer dereference caused by uninitialized group->iommufd
group->iommufd is not initialized for the iommufd_ctx_put()
[20018.331541] BUG: kernel NULL pointer dereference, address: 0000000000000000
[20018.377508] RIP: 0010:iommufd_ctx_put+0x5/0x10 [iommufd]
...
[20018.476483] Call Trace:
[20018.479214] [20018.481555] vfio_group_fops_unl_ioctl+0x506/0x690 [vfio]
[20018.487586] __x64_sys_ioctl+0x6a/0xb0
[20018.491773] ? trace_hardirqs_on+0xc5/0xe0
[20018.496347] do_syscall_64+0x67/0x90
[20018.500340] entry_SYSCALL_64_after_hwframe+0x4b/0xb5
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Wiz
CVE-2025-68761 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68761 CVE-2025-68761 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68761 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfs: fix potential use after free in hfs_correct_next_unused_CNID()
This code calls hfs_bnode_put(node) which drops the refcount and then
dreferences "node" on the next line. It's only safe to use "node"
when we're holding a reference so flip these two lines around.
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Sever
Wiz
CVE-2022-50714 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50714 CVE-2022-50714 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50714 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7921e: fix rmmod crash in driver reload test
In insmod/rmmod stress test, the following crash dump shows up immediately.
The problem is caused by missing mt76_dev in mt7921_pci_remove(). We
should make sure the drvdata is ready before probe() finished.
[168.862789] ==================================================================
[168.862797] BUG: KASAN: user-memory-access in try_to_grab_pending+0x59/0x480
[168.862805] Write of size 8 at addr 0000000000006df0 by task rmmod/5361
[168.862812] CPU: 7 PID: 5361 Comm: rmmod Tainted: G OE 5.19.0-rc6 #1
[168.862816] Hardware name: Intel(R) Client Systems NUC8i7BEH/NUC8BEB, 05/04/2020
[168.8
Wiz
CVE-2026-22990 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22990 [MEDIUM] CVE-2026-22990 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22990 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: replace overzealous BUG_ON in osdmap_apply_incremental()
If the osdmap is (maliciously) corrupted such that the incremental
osdmap epoch is different from what is expected, there is no need to
BUG. Instead, just declare the incremental osdmap to be invalid.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-trace
linux-gcp-6.8
Wiz
CVE-2025-71196 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71196 CVE-2025-71196 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71196 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
phy: stm32-usphyc: Fix off by one in probe()
The "index" variable is used as an index into the usbphyc->phys[] array
which has usbphyc->nphys elements. So if it is equal to usbphyc->nphys
then it is one element out of bounds. The "index" comes from the
device tree so it's data that we trust and it's unlikely to be wrong,
however it's obviously still worth fixing the bug. Change the > to >=.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.2
Exploit
Wiz
CVE-2026-23084 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23084 [MEDIUM] CVE-2026-23084 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23084 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
be2net: Fix NULL pointer dereference in be_cmd_get_mac_from_list
When the parameter pmac_id_valid argument of be_cmd_get_mac_from_list() is
set to false, the driver may request the PMAC_ID from the firmware of the
network card, and this function will store that PMAC_ID at the provided
address pmac_id. This is the contract of this function.
However, there is a location within the driver where both
pmac_id_valid == false and pmac_id == NULL are being passed. This could
result in dereferencing a NULL pointer.
To resolve this issue, it is necessary to pass the address of a stub
variable to the function.
Source : NVD
## 5.5
Score
Published Februa
Wiz
CVE-2025-71227 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71227 [MEDIUM] CVE-2025-71227 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71227 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: don't WARN for connections on invalid channels
It's not clear (to me) how exactly syzbot managed to hit this,
but it seems conceivable that e.g. regulatory changed and has
disabled a channel between scanning (channel is checked to be
usable by cfg80211_get_ies_channel_number) and connecting on
the channel later.
With one scenario that isn't covered elsewhere described above,
the warning isn't good, replace it with a (more informative)
error message.
Source : NVD
## 5.5
Score
Published February 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploi
Wiz
CVE-2022-50721 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50721 CVE-2022-50721 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50721 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: qcom-adm: fix wrong calling convention for prep_slave_sg
The calling convention for pre_slave_sg is to return NULL on error and
provide an error log to the system. Qcom-adm instead provide error
pointer when an error occur. This indirectly cause kernel panic for
example for the nandc driver that checks only if the pointer returned by
device_prep_slave_sg is not NULL. Returning an error pointer makes nandc
think the device_prep_slave_sg function correctly completed and makes
the kernel panics later in the code.
While nandc is the one that makes the kernel crash, it was pointed out
that the real problem is qcom-adm not following calling co
Wiz
CVE-2023-54235 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54235 CVE-2023-54235 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54235 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI/DOE: Fix destroy_work_on_stack() race
The following debug object splat was observed in testing:
ODEBUG: free active (active state 0) object: 0000000097d23782 object type: work_struct hint: doe_statemachine_work+0x0/0x510
WARNING: CPU: 1 PID: 71 at lib/debugobjects.c:514 debug_print_object+0x7d/0xb0
...
Workqueue: pci 0000:36:00.0 DOE [1 doe_statemachine_work
RIP: 0010:debug_print_object+0x7d/0xb0
...
Call Trace:
? debug_print_object+0x7d/0xb0
? __pfx_doe_statemachine_work+0x10/0x10
debug_object_free.part.0+0x11b/0x150
doe_statemachine_work+0x45e/0x510
process_one_work+0x1d4/0x3c0
This occurs because destroy_work_on_stack() was called after sig
Wiz
CVE-2026-31398 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31398 CVE-2026-31398 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31398 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/rmap: fix incorrect pte restoration for lazyfree folios
We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the
batch has a mix of writable and non-writable bits, we may end up setting
the entire batch writable. Fix this by respecting writable bit during
batching.
Although on a successful unmap of a lazyfree folio, the soft-dirty bit is
lost, preserve it on pte restoration by respecting the bit during
batching, to make the fix consistent w.r.t both writable bit and
soft-dirty bit.
I was able to write the below reproducer and crash the kernel.
Explanation of reproducer (set 64K mTHP to always):
Fault in a 64K large folio. Spli
Wiz
CVE-2026-23082 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23082 [MEDIUM] CVE-2026-23082 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23082 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_receive_bulk_callback(): unanchor URL on usb_submit_urb() error
In commit 7352e1d5932a ("can: gs_usb: gs_usb_receive_bulk_callback(): fix
URB memory leak"), the URB was re-anchored before usb_submit_urb() in
gs_usb_receive_bulk_callback() to prevent a leak of this URB during
cleanup.
However, this patch did not take into account that usb_submit_urb() could
fail. The URB remains anchored and
usb_kill_anchored_urbs(&parent->rx_submitted) in gs_can_close() loops
infinitely since the anchor list never becomes empty.
To fix the bug, unanchor the URB when an usb_submit_urb() error occurs,
also print an info message.
Source : NVD
#
Wiz
CVE-2023-53864 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53864 CVE-2023-53864 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53864 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/mxsfb: Disable overlay plane in mxsfb_plane_overlay_atomic_disable()
When disabling overlay plane in mxsfb_plane_overlay_atomic_update(),
overlay plane's framebuffer pointer is NULL. So, dereferencing it would
cause a kernel Oops(NULL pointer dereferencing). Fix the issue by
disabling overlay plane in mxsfb_plane_overlay_atomic_disable() instead.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected pac
Wiz
CVE-2026-23299 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23299 CVE-2026-23299 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23299 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: purge error queues in socket destructors
When TX timestamping is enabled via SO_TIMESTAMPING, SKBs may be queued
into sk_error_queue and will stay there until consumed. If userspace never
gets to read the timestamps, or if the controller is removed unexpectedly,
these SKBs will leak.
Fix by adding skb_queue_purge() calls for sk_error_queue in affected
bluetooth destructors. RFCOMM does not currently use sk_error_queue.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Prob
Wiz
CVE-2025-68347 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68347 CVE-2025-68347 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68347 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: firewire-motu: fix buffer overflow in hwdep read for DSP events
The DSP event handling code in hwdep_read() could write more bytes to
the user buffer than requested, when a user provides a buffer smaller
than the event header size (8 bytes).
Fix by using min_t() to clamp the copy size, This ensures we never copy
more than the user requested.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 20.2
Exploitation Pro
Wiz
CVE-2023-54236 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54236 CVE-2023-54236 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54236 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/net_failover: fix txq exceeding warning
The failover txq is inited as 16 queues.
when a packet is transmitted from the failover device firstly,
the failover device will select the queue which is returned from
the primary device if the primary device is UP and running.
If the primary device txq is bigger than the default 16,
it can lead to the following warning:
eth0 selects TX queue 18, but real number of TX queues is 16
The warning backtrace is:
[ 32.146376] CPU: 18 PID: 9134 Comm: chronyd Tainted: G E 6.2.8-1.el7.centos.x86_64 #1
[ 32.147175] Hardware name: Red Hat KVM, BIOS 1.10.2-3.el7_4.1 04/01/2014
[ 32.147730] Call Trace:
[ 32.147971] [
Wiz
CVE-2026-23127 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23127 [MEDIUM] CVE-2026-23127 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23127 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf: Fix refcount warning on event->mmap_count increment
When calling refcount_inc(&event->mmap_count) inside perf_mmap_rb(), the
following warning is triggered:
refcount_t: addition on 0; use-after-free.
WARNING: lib/refcount.c:25
PoC:
struct perf_event_attr attr = {0};
int fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
mmap(NULL, 0x3000, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
int victim = syscall(__NR_perf_event_open, &attr, 0, -1, fd,
PERF_FLAG_FD_OUTPUT);
mmap(NULL, 0x3000, PROT_READ | PROT_WRITE, MAP_SHARED, victim, 0);
This occurs when creating a group member event with the flag
PERF_FLAG_FD_OUTPUT. The group leader should
Wiz
CVE-2025-68213 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68213 CVE-2025-68213 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68213 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix possible vport_config NULL pointer deref in remove
Attempting to remove the driver will cause a crash in cases where
the vport failed to initialize. Following trace is from an instance where
the driver failed during an attempt to create a VF:
[ 1661.543624] idpf 0000:84:00.7: Device HW Reset initiated
[ 1722.923726] idpf 0000:84:00.7: Transaction timed-out (op:1 cookie:2900 vc_op:1 salt:29 timeout:60000ms)
[ 1723.353263] BUG: kernel NULL pointer dereference, address: 0000000000000028
...
[ 1723.358472] RIP: 0010:idpf_remove+0x11c/0x200 [idpf]
...
[ 1723.364973] Call Trace:
[ 1723.365475] [ 1723.365972] pci_device_remove+0x42/0xb0
[ 1723.36
Wiz
CVE-2022-50742 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50742 CVE-2022-50742 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50742 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
misc: ocxl: fix possible refcount leak in afu_ioctl()
eventfd_ctx_put need to be called to put the refcount that gotten by
eventfd_ctx_fdget when ocxl_irq_set_handler fails.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-oracle
kernel-debug-core
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8, 9 Sever
Wiz
CVE-2026-23183 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23183 CVE-2026-23183 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23183 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cgroup/dmem: fix NULL pointer dereference when setting max
An issue was triggered:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 15 UID: 0 PID: 658 Comm: bash Tainted: 6.19.0-rc6-next-2026012
Tainted: [O]=OOT_MODULE
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
RIP: 0010:strcmp+0x10/0x30
RSP: 0018:ffffc900017f7dc0 EFLAGS: 00000246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff888107cd4358
RDX: 0000000019f73907 RSI: ffffffff82cc381a RDI: 0000000000000000
RBP: ffff8881016bef0d R08: 00
Wiz
CVE-2026-23025 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23025 [HIGH] CVE-2026-23025 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23025 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/page_alloc: prevent pcp corruption with SMP=n
The kernel test robot has reported:
BUG: spinlock trylock failure on UP on CPU#0, kcompactd0/28
lock: 0xffff888807e35ef0, .magic: dead4ead, .owner: kcompactd0/28, .owner_cpu: 0
CPU: 0 UID: 0 PID: 28 Comm: kcompactd0 Not tainted 6.18.0-rc5-00127-ga06157804399 #1 PREEMPT 8cc09ef94dcec767faa911515ce9e609c45db470
Call Trace: __dump_stack (lib/dump_stack.c:95)
dump_stack_lvl (lib/dump_stack.c:123)
dump_stack (lib/dump_stack.c:130)
spin_dump (kernel/locking/spinlock_debug.c:71)
do_raw_spin_trylock (kernel/locking/spinlock_debug.c:?)
_raw_spin_trylock (include/linux/spinlock_api_smp.h:89 kernel/locking/spin
Wiz
CVE-2022-50726 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50726 CVE-2022-50726 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50726 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5: Fix possible use-after-free in async command interface
mlx5_cmd_cleanup_async_ctx should return only after all its callback
handlers were completed. Before this patch, the below race between
mlx5_cmd_cleanup_async_ctx and mlx5_cmd_exec_cb_handler was possible and
lead to a use-after-free:
mlx5_cmd_cleanup_async_ctx is called while num_inflight is 2 (i.e.
elevated by 1, a single inflight callback).
mlx5_cmd_cleanup_async_ctx decreases num_inflight to 1.
mlx5_cmd_exec_cb_handler is called, decreases num_inflight to 0 and is about to call wake_up().
mlx5_cmd_cleanup_async_ctx calls wait_event, which returns immediately as the condition (n
Wiz
CVE-2023-54294 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54294 CVE-2023-54294 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54294 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid10: fix memleak of md thread
In raid10_run(), if setup_conf() succeed and raid10_run() failed before
setting 'mddev->thread', then in the error path 'conf->thread' is not
freed.
Fix the problem by setting 'mddev->thread' right after setup_conf().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug-modules
kernel-rt-modules-core
Sources
NVD
Debian 11,
Wiz
CVE-2023-54230 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54230 CVE-2023-54230 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54230 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
amba: bus: fix refcount leak
commit 5de1540b7bc4 ("drivers/amba: create devices from device tree")
increases the refcount of of_node, but not releases it in
amba_device_release, so there is refcount leak. By using of_node_put
to avoid refcount leak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug-kvm
kernel-debug
Sources
NVD
Debian 11, 12, 13, 14 Has F
Wiz
CVE-2025-68190 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68190 CVE-2025-68190 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68190 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu/atom: Check kcalloc() for WS buffer in amdgpu_atom_execute_table_locked()
kcalloc() may fail. When WS is non-zero and allocation fails, ectx.ws
remains NULL while ectx.ws_size is set, leading to a potential NULL
pointer dereference in atom_get_src_int() when accessing WS entries.
Return -ENOMEM on allocation failure to avoid the NULL dereference.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploita
Wiz
CVE-2025-68309 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68309 CVE-2025-68309 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68309 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI/AER: Fix NULL pointer access by aer_info
The kzalloc(GFP_KERNEL) may return NULL, so all accesses to aer_info->xxx
will result in kernel panic. Fix it.
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-realtime
kernel
Sources
NVD
Debian 11, 12, 13 No Fix Added at: Dec 17, 2025
Debian 14 Has Fix Added at: Dec 17, 2025
Echo Has Fix
Wiz
CVE-2025-68742 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68742 CVE-2025-68742 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68742 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix invalid prog->stats access when update_effective_progs fails
Syzkaller triggers an invalid memory access issue following fault
injection in update_effective_progs. The issue can be described as
follows:
__cgroup_bpf_detach
update_effective_progs
compute_effective_progs
bpf_prog_array_alloc items[index] = &dummy_bpf_prog.prog
---softirq start---
__do_softirq
...
__cgroup_bpf_run_filter_skb
__bpf_prog_run_save_cb
bpf_prog_run
stats = this_cpu_ptr(prog->stats)
/* invalid memory access */
flags = u64_stats_update_begin_irqsave(&stats->syncp)
---softirq end---
static_branch_dec(&cgroup_bpf_enabled_key[atype])
The reason is that fault injecti
Wiz
CVE-2026-23192 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23192 [HIGH] CVE-2026-23192 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23192 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
linkwatch: use __dev_put() in callers to prevent UAF
After linkwatch_do_dev() calls __dev_put() to release the linkwatch
reference, the device refcount may drop to 1. At this point,
netdev_run_todo() can proceed (since linkwatch_sync_dev() sees an
empty list and returns without blocking), wait for the refcount to
become 1 via netdev_wait_allrefs_any(), and then free the device
via kobject_put().
This creates a use-after-free when __linkwatch_run_queue() tries to
call netdev_unlock_ops() on the already-freed device.
Note that adding netdev_lock_ops()/netdev_unlock_ops() pair in
netdev_run_todo() before kobject_put() would not work, because
netdev_l
Wiz
CVE-2023-54039 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54039 CVE-2023-54039 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54039 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: j1939: j1939_tp_tx_dat_new(): fix out-of-bounds memory access
In the j1939_tp_tx_dat_new() function, an out-of-bounds memory access
could occur during the memcpy() operation if the size of skb->cb is
larger than the size of struct j1939_sk_buff_cb. This is because the
memcpy() operation uses the size of skb->cb, leading to a read beyond
the struct j1939_sk_buff_cb.
Updated the memcpy() operation to use the size of struct
j1939_sk_buff_cb instead of the size of skb->cb. This ensures that the
memcpy() operation only reads the memory within the bounds of struct
j1939_sk_buff_cb, preventing out-of-bounds memory access.
Additionally, add a BUILD_B
Wiz
CVE-2023-54324 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54324 CVE-2023-54324 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54324 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm: fix a race condition in retrieve_deps
There's a race condition in the multipath target when retrieve_deps
races with multipath_message calling dm_get_device and dm_put_device.
retrieve_deps walks the list of open devices without holding any lock
but multipath may add or remove devices to the list while it is
running. The end result may be memory corruption or use-after-free
memory access.
See this description of a UAF with multipath_message(): https://listman.redhat.com/archives/dm-devel/2022-October/052373.html
Fix this bug by introducing a new rw semaphore "devices_lock". We grab
devices_lock for read in retrieve_deps and we grab it for writ
Wiz
CVE-2026-31390 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31390 CVE-2026-31390 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31390 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe: Fix memory leak in xe_vm_madvise_ioctl
When check_bo_args_are_sane() validation fails, jump to the new
free_vmas cleanup label to properly free the allocated resources.
This ensures proper cleanup in this error path.
(cherry picked from commit 29bd06faf727a4b76663e4be0f7d770e2d2a7965)
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gcp-fips
kernel-64k-debug-modules-i
Wiz
CVE-2025-68242 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68242 CVE-2025-68242 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68242 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFS: Fix LTP test failures when timestamps are delegated
The utimes01 and utime06 tests fail when delegated timestamps are
enabled, specifically in subtests that modify the atime and mtime
fields using the 'nobody' user ID.
The problem can be reproduced as follow:
## echo "/media *(rw,no_root_squash,sync)" >> /etc/exports
## export -ra
## mount -o rw,nfsvers=4.2 127.0.0.1:/media /tmpdir
## cd /opt/ltp
## ./runltp -d /tmpdir -s utimes01
## ./runltp -d /tmpdir -s utime06
This issue occurs because nfs_setattr does not verify the inode's
UID against the caller's fsuid when delegated timestamps are
permitted for the inode.
This patch adds
Wiz
CVE-2025-68300 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68300 CVE-2025-68300 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68300 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/namespace: fix reference leak in grab_requested_mnt_ns
lookup_mnt_ns() already takes a reference on mnt_ns.
grab_requested_mnt_ns() doesn't need to take an extra reference.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-core
kernel-rt-64k-modules-internal
Sources
NVD
Debian 13 No Fix Added at: Dec 17, 2025
Debian 14 Has Fix Added at: Dec 17, 2025
R
Wiz
CVE-2026-23321 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23321 CVE-2026-23321 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23321 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: pm: in-kernel: always mark signal+subflow endp as used
Syzkaller managed to find a combination of actions that was generating
this warning:
msk->pm.local_addr_used == 0
WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961
WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961
WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961
Modules linked in:
CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b0
Wiz
CVE-2023-54234 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54234 CVE-2023-54234 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54234 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: mpi3mr: Fix missing mrioc->evtack_cmds initialization
Commit c1af985d27da ("scsi: mpi3mr: Add Event acknowledgment logic")
introduced an array mrioc->evtack_cmds but initialization of the array
elements was missed. They are just zero cleared. The function
mpi3mr_complete_evt_ack() refers host_tag field of the elements. Due to the
zero value of the host_tag field, the function calls clear_bit() for
mrico->evtack_cmds_bitmap with wrong bit index. This results in memory
access to invalid address and "BUG: KASAN: use-after-free". This BUG was
observed at eHBA-9600 firmware update to version 8.3.1.0. To fix it, add
the missing initialization of mri
Wiz
CVE-2026-23009 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23009 [MEDIUM] CVE-2026-23009 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23009 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xhci: sideband: don't dereference freed ring when removing sideband endpoint
xhci_sideband_remove_endpoint() incorrecly assumes that the endpoint is
running and has a valid transfer ring.
Lianqin reported a crash during suspend/wake-up stress testing, and
found the cause to be dereferencing a non-existing transfer ring
'ep->ring' during xhci_sideband_remove_endpoint().
The endpoint and its ring may be in unknown state if this function
is called after xHCI was reinitialized in resume (lost power), or if
device is being re-enumerated, disconnected or endpoint already dropped.
Fix this by both removing unnecessary ring access, and by checking
ep->ri
Wiz
CVE-2025-40348 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40348 CVE-2025-40348 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40348 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
slab: Avoid race on slab->obj_exts in alloc_slab_obj_exts
If two competing threads enter alloc_slab_obj_exts() and one of them
fails to allocate the object extension vector, it might override the
valid slab->obj_exts allocated by the other thread with
OBJEXTS_ALLOC_FAIL. This will cause the thread that lost this race and
expects a valid pointer to dereference a NULL pointer later on.
Update slab->obj_exts atomically using cmpxchg() to avoid
slab->obj_exts overrides by racing threads.
Thanks for Vlastimil and Suren's help with debugging.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Ha
Wiz
CVE-2023-54063 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54063 CVE-2023-54063 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54063 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix OOB read in indx_insert_into_buffer
Syzbot reported a OOB read bug:
BUG: KASAN: slab-out-of-bounds in indx_insert_into_buffer+0xaa3/0x13b0
fs/ntfs3/index.c:1755
Read of size 17168 at addr ffff8880255e06c0 by task syz-executor308/3630
Call Trace: memmove+0x25/0x60 mm/kasan/shadow.c:54
indx_insert_into_buffer+0xaa3/0x13b0 fs/ntfs3/index.c:1755
indx_insert_entry+0x446/0x6b0 fs/ntfs3/index.c:1863
ntfs_create_inode+0x1d3f/0x35c0 fs/ntfs3/inode.c:1548
ntfs_create+0x3e/0x60 fs/ntfs3/namei.c:100
lookup_open fs/namei.c:3413 [inline]
If the member struct INDEX_BUFFER *index of struct indx_node is
incorrect, that is, the value of __le32 used i
Wiz
CVE-2026-23131 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23131 [MEDIUM] CVE-2026-23131 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23131 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: hp-bioscfg: Fix kobject warnings for empty attribute names
The hp-bioscfg driver attempts to register kobjects with empty names when
the HP BIOS returns attributes with empty name strings. This causes
multiple kernel warnings:
kobject: (00000000135fb5e6): attempted to be registered with empty name!
WARNING: CPU: 14 PID: 3336 at lib/kobject.c:219 kobject_add_internal+0x2eb/0x310
Add validation in hp_init_bios_buffer_attribute() to check if the
attribute name is empty after parsing it from the WMI buffer. If empty,
log a debug message and skip registration of that attribute, allowing the
module to continue processing other valid attrib
Wiz
CVE-2026-23303 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23303 CVE-2026-23303 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23303 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: Don't log plaintext credentials in cifs_set_cifscreds
When debug logging is enabled, cifs_set_cifscreds() logs the key
payload and exposes the plaintext username and password. Remove the
debug log to avoid exposing credentials.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-6.17
linux-azure-fde-6.14
Sources
NVD
CBL-Ma
Wiz
CVE-2022-50818 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50818 CVE-2022-50818 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50818 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: pm8001: Fix running_req for internal abort commands
Disabling the remote phy for a SATA disk causes a hang:
root@(none)$ more /sys/class/sas_phy/phy-0:0:8/target_port_protocols
sata
root@(none)$ echo 0 > sys/class/sas_phy/phy-0:0:8/enable
root@(none)$ [ 67.855950] sas: ex 500e004aaaaaaa1f phy08 change count has changed
[ 67.920585] sd 0:0:2:0: [sdc] Synchronizing SCSI cache
[ 67.925780] sd 0:0:2:0: [sdc] Synchronize Cache(10) failed: Result: hostbyte=0x04 driverbyte=DRIVER_OK
[ 67.935094] sd 0:0:2:0: [sdc] Stopping disk
[ 67.939305] sd 0:0:2:0: [sdc] Start/Stop Unit failed: Result: hostbyte=0x04 driverbyte=DRIVER_OK
...
[ 123.998998] INFO: ta
Wiz
CVE-2023-54287 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54287 CVE-2023-54287 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54287 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tty: serial: imx: disable Ageing Timer interrupt request irq
There maybe pending USR interrupt before requesting irq, however
uart_add_one_port has not executed, so there will be kernel panic:
[ 0.795668] Unable to handle kernel NULL pointer dereference at virtual addre
ss 0000000000000080
[ 0.802701] Mem abort info:
[ 0.805367] ESR = 0x0000000096000004
[ 0.808950] EC = 0x25: DABT (current EL), IL = 32 bits
[ 0.814033] SET = 0, FnV = 0
[ 0.816950] EA = 0, S1PTW = 0
[ 0.819950] FSC = 0x04: level 0 translation fault
[ 0.824617] Data abort info:
[ 0.827367] ISV = 0, ISS = 0x00000004
[ 0.831033] CM = 0, WnR = 0
[ 0.833866] [0000000000000080] user addres
Wiz
CVE-2023-54055 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54055 CVE-2023-54055 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54055 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/irdma: Fix memory leak of PBLE objects
On rmmod of irdma, the PBLE object memory is not being freed. PBLE object
memory are not statically pre-allocated at function initialization time
unlike other HMC objects. PBLEs objects and the Segment Descriptors (SD)
for it can be dynamically allocated during scale up and SD's remain
allocated till function deinitialization.
Fix this leak by adding IRDMA_HMC_IW_PBLE to the iw_hmc_obj_types[] table
and skip pbles in irdma_create_hmc_obj but not in irdma_del_hmc_objects().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
H
Wiz
CVE-2025-68728 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68728 CVE-2025-68728 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68728 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ntfs3: fix uninit memory after failed mi_read in mi_format_new
Fix a KMSAN un-init bug found by syzkaller.
ntfs_get_bh() expects a buffer from sb_getblk(), that buffer may not be
uptodate. We do not bring the buffer uptodate before setting it as
uptodate. If the buffer were to not be uptodate, it could mean adding a
buffer with un-init data to the mi record. Attempting to load that record
will trigger KMSAN.
Avoid this by setting the buffer as uptodate, if it’s not already, by
overwriting it.
Source : NVD
## 4.7
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Ex
Wiz
CVE-2023-54321 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2023-54321 [MEDIUM] CVE-2023-54321 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54321 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
driver core: fix potential null-ptr-deref in device_add()
I got the following null-ptr-deref report while doing fault injection test:
BUG: kernel NULL pointer dereference, address: 0000000000000058
CPU: 2 PID: 278 Comm: 37-i2c-ds2482 Tainted: G B W N 6.1.0-rc3+
RIP: 0010:klist_put+0x2d/0xd0
Call Trace: klist_remove+0xf1/0x1c0
device_release_driver_internal+0x196/0x210
bus_remove_device+0x1bd/0x240
device_add+0xd3d/0x1100
w1_add_master_device+0x476/0x490 [wire]
ds2482_probe+0x303/0x3e0 [ds2482]
This is how it happened:
w1_alloc_dev()
// The dev->driver is set to w1_master_driver.
memcpy(&dev->dev, device, sizeof(struct device));
device_add()
bus_a
Wiz
CVE-2023-54072 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54072 CVE-2023-54072 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54072 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: pcm: Fix potential data race at PCM memory allocation helpers
The PCM memory allocation helpers have a sanity check against too many
buffer allocations. However, the check is performed without a proper
lock and the allocation isn't serialized; this allows user to allocate
more memories than predefined max size.
Practically seen, this isn't really a big problem, as it's more or
less some "soft limit" as a sanity check, and it's not possible to
allocate unlimitedly. But it's still better to address this for more
consistent behavior.
The patch covers the size check in do_alloc_pages() with the
card->memory_mutex, and increases the allocated siz
Wiz
CVE-2025-71163 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71163 [MEDIUM] CVE-2025-71163 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71163 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: idxd: fix device leaks on compat bind and unbind
Make sure to drop the reference taken when looking up the idxd device as
part of the compat bind and unbind sysfs interface.
Source : NVD
## 5.5
Score
Published January 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel
dtb-rockchip
Sources
NVD
CBL-Mariner 2.0 Severity MEDIUM Has Fix Added at: Mar 10, 2026
Debian 11 Seve
Wiz
CVE-2026-23399 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23399 CVE-2026-23399 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23399 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nf_tables: nft_dynset: fix possible stateful expression memleak in error path
If cloning the second stateful expression in the element via GFP_ATOMIC
fails, then the first stateful expression remains in place without being
released.
unreferenced object (percpu) 0x607b97e9cab8 (size 16):
comm "softirq", pid 0, jiffies 4294931867
hex dump (first 16 bytes on cpu 3):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
backtrace (crc 0):
pcpu_alloc_noprof+0x453/0xd80
nft_counter_clone+0x9c/0x190 [nf_tables]
nft_expr_clone+0x8f/0x1b0 [nf_tables]
nft_dynset_new+0x2cb/0x5f0 [nf_tables]
nft_rhash_update+0x236/0x11c0 [nf_tables]
nft_dynset_eval+0x11f/0x670 [nf_t
Wiz
CVE-2026-23045 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23045 CVE-2026-23045 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23045 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/ena: fix missing lock when update devlink params
Fix assert lock warning while calling devl_param_driverinit_value_set()
in ena.
WARNING: net/devlink/core.c:261 at devl_assert_locked+0x62/0x90, CPU#0: kworker/0:0/9
CPU: 0 UID: 0 PID: 9 Comm: kworker/0:0 Not tainted 6.19.0-rc2+ #1 PREEMPT(lazy)
Hardware name: Amazon EC2 m8i-flex.4xlarge/, BIOS 1.0 10/16/2017
Workqueue: events work_for_cpu_fn
RIP: 0010:devl_assert_locked+0x62/0x90
Call Trace: devl_param_driverinit_value_set+0x15/0x1c0
ena_devlink_alloc+0x18c/0x220 [ena]
? __pfx_ena_devlink_alloc+0x10/0x10 [ena]
? trace_hardirqs_on+0x18/0x140
? lockdep_hardirqs_on+0x8c/0x130
? __raw_spin_unlock_i
Wiz
CVE-2025-68803 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68803 CVE-2025-68803 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68803 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSD: NFSv4 file creation neglects setting ACL
An NFSv4 client that sets an ACL with a named principal during file
creation retrieves the ACL afterwards, and finds that it is only a
default ACL (based on the mode bits) and not the ACL that was
requested during file creation. This violates RFC 8881 section
6.4.1.3: "the ACL attribute is set as given".
The issue occurs in nfsd_create_setattr(), which calls
nfsd_attrs_valid() to determine whether to call nfsd_setattr().
However, nfsd_attrs_valid() checks only for iattr changes and
security labels, but not POSIX ACLs. When only an ACL is present,
the function returns false, nfsd_setattr() is skipped, a
Wiz
CVE-2026-23037 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23037 CVE-2026-23037 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23037 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: etas_es58x: allow partial RX URB allocation to succeed
When es58x_alloc_rx_urbs() fails to allocate the requested number of
URBs but succeeds in allocating some, it returns an error code.
This causes es58x_open() to return early, skipping the cleanup label
'free_urbs', which leads to the anchored URBs being leaked.
As pointed out by maintainer Vincent Mailhol, the driver is designed
to handle partial URB allocation gracefully. Therefore, partial
allocation should not be treated as a fatal error.
Modify es58x_alloc_rx_urbs() to return 0 if at least one URB has been
allocated, restoring the intended behavior and preventing the leak
in es58x_ope
Wiz
CVE-2025-71070 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71070 CVE-2025-71070 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71070 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ublk: clean up user copy references on ublk server exit
If a ublk server process releases a ublk char device file, any requests
dispatched to the ublk server but not yet completed will retain a ref
value of UBLK_REFCOUNT_INIT. Before commit e63d2228ef83 ("ublk: simplify
aborting ublk request"), __ublk_fail_req() would decrement the reference
count before completing the failed request. However, that commit
optimized __ublk_fail_req() to call __ublk_complete_rq() directly
without decrementing the request reference count.
The leaked reference count incorrectly allows user copy and zero copy
operations on the completed ublk request. It also triggers the
Wiz
CVE-2023-54223 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54223 CVE-2023-54223 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54223 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: xsk: Fix invalid buffer access for legacy rq
The below crash can be encountered when using xdpsock in rx mode for
legacy rq: the buffer gets released in the XDP_REDIRECT path, and then
once again in the driver. This fix sets the flag to avoid releasing on
the driver side.
XSK handling of buffers for legacy rq was relying on the caller to set
the skip release flag. But the referenced fix started using fragment
counts for pages instead of the skip flag.
Crash log:
general protection fault, probably for non-canonical address 0xffff8881217e3a: 0000 [#1] SMP
CPU: 0 PID: 14 Comm: ksoftirqd/0 Not tainted 6.5.0-rc1+ #31
Hardware name: QEMU Stan
Wiz
CVE-2025-68374 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68374 CVE-2025-68374 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68374 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md: fix rcu protection in md_wakeup_thread
We attempted to use RCU to protect the pointer 'thread', but directly
passed the value when calling md_wakeup_thread(). This means that the
RCU pointer has been acquired before rcu_read_lock(), which renders
rcu_read_lock() ineffective and could lead to a use-after-free.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2025-68780 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68780 CVE-2025-68780 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68780 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sched/deadline: only set free_cpus for online runqueues
Commit 16b269436b72 ("sched/deadline: Modify cpudl::free_cpus
to reflect rd->online") introduced the cpudl_set/clear_freecpu
functions to allow the cpu_dl::free_cpus mask to be manipulated
by the deadline scheduler class rq_on/offline callbacks so the
mask would also reflect this state.
Commit 9659e1eeee28 ("sched/deadline: Remove cpu_active_mask
from cpudl_find()") removed the check of the cpu_active_mask to
save some processing on the premise that the cpudl::free_cpus
mask already reflected the runqueue online state.
Unfortunately, there are cases where it is possible for the
cpudl_clear fu
Wiz
CVE-2025-68321 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68321 CVE-2025-68321 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68321 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
page_pool: always add GFP_NOWARN for ATOMIC allocations
Driver authors often forget to add GFP_NOWARN for page allocation
from the datapath. This is annoying to users as OOMs are a fact
of life, and we pretty much expect network Rx to hit page allocation
failures during OOM. Make page pool add GFP_NOWARN for ATOMIC allocations
by default.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and
Wiz
CVE-2025-68288 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.3
CVE-2025-68288 [MEDIUM] CVE-2025-68288 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68288 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: storage: Fix memory leak in USB bulk transport
A kernel memory leak was identified by the 'ioctl_sg01' test from Linux
Test Project (LTP). The following bytes were mainly observed: 0x53425355.
When USB storage devices incorrectly skip the data phase with status data,
the code extracts/validates the CSW from the sg buffer, but fails to clear
it afterwards. This leaves status protocol data in srb's transfer buffer,
such as the US_BULK_CS_SIGN 'USBS' signature observed here. Thus, this can
lead to USB protocols leaks to user space through SCSI generic (/dev/sg*)
interfaces, such as the one seen here when the LTP test requested 512 KiB.
Fix the l
Wiz
CVE-2023-54169 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54169 CVE-2023-54169 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54169 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: fix memory leak in mlx5e_ptp_open
When kvzalloc_node or kvzalloc failed in mlx5e_ptp_open, the memory
pointed by "c" or "cparams" is not freed, which can lead to a memory
leak. Fix by freeing the array in the error path.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-source-vanilla
dtb-marvell
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Wiz
CVE-2023-54078 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54078 CVE-2023-54078 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54078 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: max9286: Free control handler
The control handler is leaked in some probe-time error paths, as well as
in the remove path. Fix it.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-source-rt
kernel-64kb-devel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04 Severity MEDIUM No Fix Added a
Wiz
CVE-2026-23004 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23004 [MEDIUM] CVE-2026-23004 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23004 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dst: fix races in rt6_uncached_list_del() and rt_del_uncached_list()
syzbot was able to crash the kernel in rt6_uncached_list_flush_dev()
in an interesting way [1]
Crash happens in list_del_init()/INIT_LIST_HEAD() while writing
list->prev, while the prior write on list->next went well.
static inline void INIT_LIST_HEAD(struct list_head *list)
{
WRITE_ONCE(list->next, list); // This went well
WRITE_ONCE(list->prev, list); // Crash, @list has been freed.
}
Issue here is that rt6_uncached_list_del() did not attempt to lock
ul->lock, as list_empty(&rt->dst.rt_uncached) returned
true because the WRITE_ONCE(list->next, list) happened on the other CPU.
Wiz
CVE-2025-68804 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68804 CVE-2025-68804 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68804 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/chrome: cros_ec_ishtp: Fix UAF after unbinding driver
cros_ec_console_log_work
The driver doesn't unregister the EC device in .remove() which should
shutdown sub-devices synchronously. Fix it.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
linux-intel-iotg
dlm-kmp-default
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Jan 14, 2026
Echo Has Fix Added at: Ja
Wiz
CVE-2026-23437 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23437 CVE-2026-23437 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23437 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: shaper: protect late read accesses to the hierarchy
We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.
This is not proper, a conversion from a ref to a locked netdev
must include a liveness check (a check if the netdev hasn't been
unregistered already). Fix the read cases (those under RCU).
Writes needs a separate change to protect from creating the
hierarchy after flush has already run.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Wiz
CVE-2023-54037 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54037 CVE-2023-54037 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54037 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: prevent NULL pointer deref during reload
Calling ethtool during reload can lead to call trace, because VSI isn't
configured for some time, but netdev is alive.
To fix it add rtnl lock for VSI deconfig and config. Set ::num_q_vectors
to 0 after freeing and add a check for ::tx/rx_rings in ring related
ethtool ops.
Add proper unroll of filters in ice_start_eth().
Reproduction:
$watch -n 0.1 -d 'ethtool -g enp24s0f0np0'
$devlink dev reload pci/0000:18:00.0 action driver_reinit
Call trace before fix:
[66303.926205] BUG: kernel NULL pointer dereference, address: 0000000000000000
[66303.926259] #PF: supervisor read access in kernel mode
[66303.92
Wiz
CVE-2025-68301 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68301 CVE-2025-68301 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68301 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: atlantic: fix fragment overflow handling in RX path
The atlantic driver can receive packets with more than MAX_SKB_FRAGS (17)
fragments when handling large multi-descriptor packets. This causes an
out-of-bounds write in skb_add_rx_frag_netmem() leading to kernel panic.
The issue occurs because the driver doesn't check the total number of
fragments before calling skb_add_rx_frag(). When a packet requires more
than MAX_SKB_FRAGS fragments, the fragment index exceeds the array bounds.
Fix by assuming there will be an extra frag if buff->len > AQ_CFG_RX_HDR_SIZE,
then all fragments are accounted for. And reusing the existing check to
prevent the
Wiz
CVE-2023-54082 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54082 CVE-2023-54082 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54082 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-doc
linux-fips
Sources
NVD
Debian 11 Has Fix Added at: Dec 26, 2025
Debian 12, 13, 14 No Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 6, 7, 8 Severity LOW No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix
Wiz
CVE-2025-71098 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71098 [MEDIUM] CVE-2025-71098 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71098 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ip6_gre: make ip6gre_header() robust
Over the years, syzbot found many ways to crash the kernel
in ip6gre_header() [1].
This involves team or bonding drivers ability to dynamically
change their dev->needed_headroom and/or dev->hard_header_len
In this particular crash mld_newpack() allocated an skb
with a too small reserve/headroom, and by the time mld_sendpack()
was called, syzbot managed to attach an ip6gre device.
[1]
skbuff: skb_under_panic: text:ffffffff8a1d69a8 len:136 put:40 head:ffff888059bc7000 data:ffff888059bc6fe8 tail:0x70 end:0x6c0 dev:team0
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:213 ! skb_under_panic net
Wiz
CVE-2025-68185 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68185 CVE-2025-68185 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68185 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfs4_setup_readdir(): insufficient locking for ->d_parent->d_inode dereferencing
Theoretically it's an oopsable race, but I don't believe one can manage
to hit it on real hardware; might become doable on a KVM, but it still
won't be easy to attack.
Anyway, it's easy to deal with - since xdr_encode_hyper() is just a call of
put_unaligned_be64(), we can put that under ->d_lock and be done with that.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Wiz
CVE-2023-54306 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54306 CVE-2023-54306 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54306 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: tls: avoid hanging tasks on the tx_lock
syzbot sent a hung task report and Eric explains that adversarial
receiver may keep RWIN at 0 for a long time, so we are not guaranteed
to make forward progress. Thread which took tx_lock and went to sleep
may not release tx_lock for hours. Use interruptible sleep where
possible and reschedule the work if it can't take the lock.
Testing: existing selftest passes
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPS
Wiz
CVE-2025-68371 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68371 CVE-2025-68371 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68371 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: smartpqi: Fix device resources accessed after device removal
Correct possible race conditions during device removal.
Previously, a scheduled work item to reset a LUN could still execute
after the device was removed, leading to use-after-free and other
resource access issues.
This race condition occurs because the abort handler may schedule a LUN
reset concurrently with device removal via sdev_destroy(), leading to
use-after-free and improper access to freed resources.
Check in the device reset handler if the device is still present in
the controller's SCSI device list before running; if not, the reset
is skipped.
Cancel any pending TMF wor
Wiz
CVE-2023-53990 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53990 CVE-2023-53990 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53990 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
SMB3: Add missing locks to protect deferred close file list
cifs_del_deferred_close function has a critical section which modifies
the deferred close file list. We must acquire deferred_lock before
calling cifs_del_deferred_close function.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-debug-modules-core
kernel-rt-devel
Sources
NVD
Debian 12, 13, 14 Has Fix Adde
Wiz
CVE-2026-23319 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23319 CVE-2026-23319 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23319 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim
The root cause of this bug is that when 'bpf_link_put' reduces the
refcount of 'shim_link->link.link' to zero, the resource is considered
released but may still be referenced via 'tr->progs_hlist' in
'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in
'bpf_shim_tramp_link_release' is deferred. During this window, another
process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.
Based on Martin KaFai Lau's suggestions, I have created a simple patch.
To fix this:
Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'.
Only increment the refcount if it is no
Wiz
CVE-2023-54165 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54165 CVE-2023-54165 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54165 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
zsmalloc: move LRU update from zs_map_object() to zs_malloc()
Under memory pressure, we sometimes observe the following crash:
[ 5694.832838] ------------[ cut here ]------------
[ 5694.842093] list_del corruption, ffff888014b6a448->next is LIST_POISON1 (dead000000000100)
[ 5694.858677] WARNING: CPU: 33 PID: 418824 at lib/list_debug.c:47 __list_del_entry_valid+0x42/0x80
[ 5694.961820] CPU: 33 PID: 418824 Comm: fuse_counters.s Kdump: loaded Tainted: G S 5.19.0-0_fbk3_rc3_hoangnhatpzsdynshrv41_10870_g85a9558a25de #1
[ 5694.990194] Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM16 05/24/2021
[ 5695.007072] RIP: 0010:__list_del_entr
Wiz
CVE-2026-23415 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23415 CVE-2026-23415 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23415 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
futex: Fix UaF between futex_key_to_node_opt() and vma_replace_policy()
During futex_key_to_node_opt() execution, vma->vm_policy is read under
speculative mmap lock and RCU. Concurrently, mbind() may call
vma_replace_policy() which frees the old mempolicy immediately via
kmem_cache_free().
This creates a race where __futex_key_to_node() dereferences a freed
mempolicy pointer, causing a use-after-free read of mpol->mode.
[ 151.412631] BUG: KASAN: slab-use-after-free in __futex_key_to_node (kernel/futex/core.c:349)
[ 151.414046] Read of size 2 at addr ffff888001c49634 by task e/87
[ 151.415969] Call Trace:
[ 151.416732] __asan_load2 (mm/kasan/gene
Wiz
CVE-2023-54200 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54200 CVE-2023-54200 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54200 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: always release netdev hooks from notifier
This reverts "netfilter: nf_tables: skip netdev events generated on netns removal".
The problem is that when a veth device is released, the veth release
callback will also queue the peer netns device for removal.
Its possible that the peer netns is also slated for removal. In this
case, the device memory is already released before the pre_exit hook of
the peer netns runs:
BUG: KASAN: slab-use-after-free in nf_hook_entry_head+0x1b8/0x1d0
Read of size 8 at addr ffff88812c0124f0 by task kworker/u8:1/45
Workqueue: netns cleanup_net
Call Trace:
nf_hook_entry_head+0x1b8/0x1d0
__nf_unregist
Wiz
CVE-2023-54202 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54202 CVE-2023-54202 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54202 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915: fix race condition UAF in i915_perf_add_config_ioctl
Userspace can guess the id value and try to race oa_config object creation
with config remove, resulting in a use-after-free if we dereference the
object after unlocking the metrics_lock. For that reason, unlocking the
metrics_lock must be done after we are done dereferencing the object.
[tursulin: Manually added stable tag.]
(cherry picked from commit 49f6f6483b652108bcb73accd0204a464b922395)
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due
Wiz
CVE-2026-23346 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23346 CVE-2026-23346 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23346 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: io: Extract user memory type in ioremap_prot()
The only caller of ioremap_prot() outside of the generic ioremap()
implementation is generic_access_phys(), which passes a 'pgprot_t' value
determined from the user mapping of the target 'pfn' being accessed by
the kernel. On arm64, the 'pgprot_t' contains all of the non-address
bits from the pte, including the permission controls, and so we end up
returning a new user mapping from ioremap_prot() which faults when
accessed from the kernel on systems with PAN:
| Unable to handle kernel read from unreadable memory at virtual address ffff80008ea89000
| ...
| Call trace:
| __memcpy_fromio+0x80/0xf8
Wiz
CVE-2025-71112 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71112 [HIGH] CVE-2025-71112 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71112 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: hns3: add VLAN id validation before using
Currently, the VLAN id may be used without validation when
receive a VLAN configuration mailbox from VF. The length of
vlan_del_fail_bmap is BITS_TO_LONGS(VLAN_N_VID). It may cause
out-of-bounds memory access once the VLAN id is bigger than
or equal to VLAN_N_VID.
Therefore, VLAN id needs to be checked to ensure it is within
the range of VLAN_N_VID.
Source : NVD
## 7.1
Score
Published January 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Proba
Wiz
CVE-2023-54075 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54075 CVE-2023-54075 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54075 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: mediatek: common: Fix refcount leak in parse_dai_link_info
Add missing of_node_put()s before the returns to balance
of_node_get()s and of_node_put()s, which may get unbalanced
in case the for loop 'for_each_available_child_of_node' returns
early.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM N
Wiz
CVE-2026-23398 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23398 CVE-2026-23398 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23398 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
icmp: fix NULL pointer dereference in icmp_tag_validation()
icmp_tag_validation() unconditionally dereferences the result of
rcu_dereference(inet_protos[proto]) without checking for NULL.
The inet_protos[] array is sparse -- only about 15 of 256 protocol
numbers have registered handlers. When ip_no_pmtu_disc is set to 3
(hardened PMTU mode) and the kernel receives an ICMP Fragmentation
Needed error with a quoted inner IP header containing an unregistered
protocol number, the NULL dereference causes a kernel panic in
softirq context.
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI
KASA
Wiz
CVE-2025-68365 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68365 [MEDIUM] CVE-2025-68365 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68365 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Initialize allocated memory before use
KMSAN reports: Multiple uninitialized values detected:
KMSAN: uninit-value in ntfs_read_hdr (3)
KMSAN: uninit-value in bcmp (3)
Memory is allocated by __getname(), which is a wrapper for
kmem_cache_alloc(). This memory is used before being properly
cleared. Change kmem_cache_alloc() to kmem_cache_zalloc() to
properly allocate and clear memory before use.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploit
Wiz
CVE-2025-68329 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68329 CVE-2025-68329 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68329 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Fix WARN_ON in tracing_buffers_mmap_close for split VMAs
When a VMA is split (e.g., by partial munmap or MAP_FIXED), the kernel
calls vm_ops->close on each portion. For trace buffer mappings, this
results in ring_buffer_unmap() being called multiple times while
ring_buffer_map() was only called once.
This causes ring_buffer_unmap() to return -ENODEV on subsequent calls
because user_mapped is already 0, triggering a WARN_ON.
Trace buffer mappings cannot support partial mappings because the ring
buffer structure requires the complete buffer including the meta page.
Fix this by adding a may_split callback that returns -EINVAL to prevent
VMA
Wiz
CVE-2026-23326 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23326 CVE-2026-23326 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23326 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xsk: Fix fragment node deletion to prevent buffer leak
After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"),
the list_node field is reused for both the xskb pool list and the buffer
free list, this causes a buffer leak as described below.
xp_free() checks if a buffer is already on the free list using
list_empty(&xskb->list_node). When list_del() is used to remove a node
from the xskb pool list, it doesn't reinitialize the node pointers.
This means list_empty() will return false even after the node has been
removed, causing xp_free() to incorrectly skip adding the buffer to the
free list.
Fix this by using list_del_init() inst
Wiz
CVE-2022-50719 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50719 CVE-2022-50719 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50719 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: line6: fix stack overflow in line6_midi_transmit
Correctly calculate available space including the size of the chunk
buffer. This fixes a buffer overflow when multiple MIDI sysex
messages are sent to a PODxt device.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 30.3
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-rt-64k-modules-core
kernel-rt-64k-modules-extra
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added a
Wiz
CVE-2023-53865 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53865 CVE-2023-53865 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53865 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix warning when putting transaction with qgroups enabled after abort
If we have a transaction abort with qgroups enabled we get a warning
triggered when doing the final put on the transaction, like this:
[552.6789] ------------[ cut here ]------------
[552.6815] WARNING: CPU: 4 PID: 81745 at fs/btrfs/transaction.c:144 btrfs_put_transaction+0x123/0x130 [btrfs]
[552.6817] Modules linked in: btrfs blake2b_generic xor (...)
[552.6819] CPU: 4 PID: 81745 Comm: btrfs-transacti Tainted: G W 6.4.0-rc6-btrfs-next-134+ #1
[552.6819] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
[552
Wiz
CVE-2025-40361 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40361 CVE-2025-40361 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40361 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-debug-core
kernel-rt-modules-internal
Sources
NVD
Container-Optimized OS Has Fix Added at: Jan 07, 2026
Debian 11, 12, 13, 14 Has Fix Added at: Dec 17, 2025
Echo Has Fix Added at: Dec 17, 2025
Red Hat 6, 7, 8, 9, 10 Severity MEDIUM No Fix Added at: Dec 17, 2025
Ubuntu 16.04, 18.04, 20.04, 2
Wiz
CVE-2022-50705 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50705 CVE-2022-50705 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50705 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/rw: defer fsnotify calls to task context
We can't call these off the kiocb completion as that might be off
soft/hard irq context. Defer the calls to when we process the
task_work for this request. That avoids valid complaints like:
stack backtrace:
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022
Call Trace: __dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
print_usage_bug kernel/locking/lockdep.c:3961 [inline]
valid_state kernel/locking/lockdep.c:3973 [inline]
mark_lock_irq ke
Wiz
CVE-2026-23102 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23102 [HIGH] CVE-2026-23102 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23102 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64/fpsimd: signal: Fix restoration of SVE context
When SME is supported, Restoring SVE signal context can go wrong in a
few ways, including placing the task into an invalid state where the
kernel may read from out-of-bounds memory (and may potentially take a
fatal fault) and/or may kill the task with a SIGKILL.
(1) Restoring a context with SVE_SIG_FLAG_SM set can place the task into
an invalid state where SVCR.SM is set (and sve_state is non-NULL)
but TIF_SME is clear, consequently resuting in out-of-bounds memory
reads and/or killing the task with SIGKILL.
This can only occur in unusual (but legitimate) cases where the SVE
signal context has e
Wiz
CVE-2023-54031 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2023-54031 [MEDIUM] CVE-2023-54031 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54031 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vdpa: Add queue index attr to vdpa_nl_policy for nlattr length check
The vdpa_nl_policy structure is used to validate the nlattr when parsing
the incoming nlmsg. It will ensure the attribute being described produces
a valid nlattr pointer in info->attrs before entering into each handler
in vdpa_nl_ops.
That is to say, the missing part in vdpa_nl_policy may lead to illegal
nlattr after parsing, which could lead to OOB read just like CVE-2023-3773.
This patch adds the missing nla_policy for vdpa queue index attr to avoid
such bugs.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Publi
Wiz
CVE-2025-68821 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68821 CVE-2025-68821 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68821 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fuse: fix readahead reclaim deadlock
Commit e26ee4efbc79 ("fuse: allocate ff->release_args only if release is
needed") skips allocating ff->release_args if the server does not
implement open. However in doing so, fuse_prepare_release() now skips
grabbing the reference on the inode, which makes it possible for an
inode to be evicted from the dcache while there are inflight readahead
requests. This causes a deadlock if the server triggers reclaim while
servicing the readahead request and reclaim attempts to evict the inode
of the file being read ahead. Since the folio is locked during
readahead, when reclaim evicts the fuse inode and fuse_evict_inode(
Wiz
CVE-2023-54251 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54251 CVE-2023-54251 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54251 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX.
syzkaller found zero division error [0] in div_s64_rem() called from
get_cycle_time_elapsed(), where sched->cycle_time is the divisor.
We have tests in parse_taprio_schedule() so that cycle_time will never
be 0, and actually cycle_time is not 0 in get_cycle_time_elapsed().
The problem is that the types of divisor are different; cycle_time is
s64, but the argument of div_s64_rem() is s32.
syzkaller fed this input and 0x100000000 is cast to s32 to be 0.
@TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME={0xc, 0x8, 0x100000000}
We use s64 for cycle_time to cast it to ktime_t, so let's keep it an
Wiz
CVE-2023-53857 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53857 CVE-2023-53857 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53857 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: bpf_sk_storage: Fix invalid wait context lockdep report
'./test_progs -t test_local_storage' reported a splat:
[ 27.137569] =============================
[ 27.138122] [ BUG: Invalid wait context ]
[ 27.138650] 6.5.0-03980-gd11ae1b16b0a #247 Tainted: G O
[ 27.139542] -----------------------------
[ 27.140106] test_progs/1729 is trying to lock:
[ 27.140713] ffff8883ef047b88 (stock_lock){-.-.}-{3:3}, at: local_lock_acquire+0x9/0x130
[ 27.141834] other info that might help us debug this:
[ 27.142437] context-{5:5}
[ 27.142856] 2 locks held by test_progs/1729:
[ 27.143352] #0: ffffffff84bcd9c0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x4/0
Wiz
CVE-2022-50869 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50869 CVE-2022-50869 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50869 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix slab-out-of-bounds in r_page
When PAGE_SIZE is 64K, if read_log_page is called by log_read_rst for
the first time, the size of *buffer would be equal to
DefaultLogPageSize(4K).But for *buffer operations like memcpy,
if the memory area size(n) which being assigned to buffer is larger
than 4K (log->page_size(64K) or bytes(64K-page_off)), it will cause
an out of boundary error.
Call trace:
[...]
kasan_report+0x44/0x130
check_memory_region+0xf8/0x1a0
memcpy+0xc8/0x100
ntfs_read_run_nb+0x20c/0x460
read_log_page+0xd0/0x1f4
log_read_rst+0x110/0x75c
log_replay+0x1e8/0x4aa0
ntfs_loadlog_and_replay+0x290/0x2d0
ntfs_fill_super+0x508/0xec0
get_tre
Wiz
CVE-2025-68800 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68800 CVE-2025-68800 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68800 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mlxsw: spectrum_mr: Fix use-after-free when updating multicast route stats
Cited commit added a dedicated mutex (instead of RTNL) to protect the
multicast route list, so that it will not change while the driver
periodically traverses it in order to update the kernel about multicast
route stats that were queried from the device.
One instance of list entry deletion (during route replace) was missed
and it can result in a use-after-free [1].
Fix by acquiring the mutex before deleting the entry from the list and
releasing it afterwards.
[1]
BUG: KASAN: slab-use-after-free in mlxsw_sp_mr_stats_update+0x4a5/0x540 drivers/net/ethernet/mellanox/mlxsw/spe
Wiz
CVE-2026-23277 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23277 CVE-2026-23277 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23277 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit
teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit
through slave devices, but does not update skb->dev to the slave device
beforehand.
When a gretap tunnel is a TEQL slave, the transmit path reaches
iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0
master) and later calls iptunnel_xmit_stats(dev, pkt_len). This
function does:
get_cpu_ptr(dev->tstats)
Since teql_master_setup() does not set dev->pcpu_stat_type to
NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats
for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL)
Wiz
CVE-2025-71125 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71125 [MEDIUM] CVE-2025-71125 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71125 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Do not register unsupported perf events
Synthetic events currently do not have a function to register perf events.
This leads to calling the tracepoint register functions with a NULL
function pointer which triggers:
------------[ cut here ]------------
WARNING: kernel/tracepoint.c:175 at tracepoint_add_func+0x357/0x370, CPU#2: perf/2272
Modules linked in: kvm_intel kvm irqbypass
CPU: 2 UID: 0 PID: 2272 Comm: perf Not tainted 6.18.0-ftest-11964-ge022764176fc-dirty #323 PREEMPTLAZY
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
RIP: 0010:tracepoint_add_func+0x357/0x370
Code: 28 9c e8 4c 0b f5 ff eb
Wiz
CVE-2026-23193 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.8
CVE-2026-23193 [HIGH] CVE-2026-23193 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23193 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: iscsi: Fix use-after-free in iscsit_dec_session_usage_count()
In iscsit_dec_session_usage_count(), the function calls complete() while
holding the sess->session_usage_lock. Similar to the connection usage count
logic, the waiter signaled by complete() (e.g., in the session release
path) may wake up and free the iscsit_session structure immediately.
This creates a race condition where the current thread may attempt to
execute spin_unlock_bh() on a session structure that has already been
deallocated, resulting in a KASAN slab-use-after-free.
To resolve this, release the session_usage_lock before calling complete()
to ensure all derefer
Wiz
CVE-2026-23273 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23273 [HIGH] CVE-2026-23273 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23273 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
macvlan: observe an RCU grace period in macvlan_common_newlink() error path
valis reported that a race condition still happens after my prior patch.
macvlan_common_newlink() might have made @dev visible before
detecting an error, and its caller will directly call free_netdev(dev).
We must respect an RCU period, either in macvlan or the core networking
stack.
After adding a temporary mdelay(1000) in macvlan_forward_source_one()
to open the race window, valis repro was:
ip link add p1 type veth peer p2
ip link set address 00:00:00:00:00:20 dev p1
ip link set up dev p1
ip link set up dev p2
ip link add mv0 link p2 type macvlan mode source
(ip link
Wiz
CVE-2026-23080 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23080 [MEDIUM] CVE-2026-23080 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23080 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: mcba_usb: mcba_usb_read_bulk_callback(): fix URB memory leak
Fix similar memory leak as in commit 7352e1d5932a ("can: gs_usb:
gs_usb_receive_bulk_callback(): fix URB memory leak").
In mcba_usb_probe() -> mcba_usb_start(), the URBs for USB-in transfers are
allocated, added to the priv->rx_submitted anchor and submitted. In the
complete callback mcba_usb_read_bulk_callback(), the URBs are processed and
resubmitted. In mcba_usb_close() -> mcba_urb_unlink() the URBs are freed by
calling usb_kill_anchored_urbs(&priv->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the complete function is cal
Wiz
CVE-2022-50809 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50809 CVE-2022-50809 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50809 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xhci: dbc: Fix memory leak in xhci_alloc_dbc()
If DbC is already in use, then the allocated memory for the xhci_dbc struct
doesn't get freed before returning NULL, which leads to a memleak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-core
kernel-rt-debug-modules-extra
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31,
Wiz
CVE-2023-54004 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54004 CVE-2023-54004 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54004 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udplite: Fix NULL pointer dereference in __sk_mem_raise_allocated().
syzbot reported 0 a null-ptr-deref in sk_get_rmem0() while using
IPPROTO_UDPLITE (0x88):
14:25:52 executing program 1:
r0 = socket$inet6(0xa, 0x80002, 0x88)
We had a similar report [1] for probably sk_memory_allocated_add()
in __sk_mem_raise_allocated(), and commit c915fe13cbaa ("udplite: fix
NULL pointer dereference") fixed it by setting .memory_allocated for
udplite_prot and udplitev6_prot.
To fix the variant, we need to set either .sysctl_wmem_offset or
.sysctl_rmem.
Now UDP and UDPLITE share the same value for .memory_allocated, so we
use the same .sysctl_wmem_offset for UD
Wiz
CVE-2025-68320 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68320 CVE-2025-68320 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68320 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
lan966x: Fix sleeping in atomic context
The following warning was seen when we try to connect using ssh to the device.
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:575
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 104, name: dropbear
preempt_count: 1, expected: 0
INFO: lockdep is turned off.
CPU: 0 UID: 0 PID: 104 Comm: dropbear Tainted: G W 6.18.0-rc2-00399-g6f1ab1b109b9-dirty #530 NONE
Tainted: [W]=WARN
Hardware name: Generic DT based system
Call trace:
unwind_backtrace from show_stack+0x10/0x14
show_stack from dump_stack_lvl+0x7c/0xac
dump_stack_lvl from __might_resched+0x16c/0x2b0
__might_resched from __
Wiz
CVE-2022-50889 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50889 CVE-2022-50889 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50889 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm integrity: Fix UAF in dm_integrity_dtr()
Dm_integrity also has the same UAF problem when dm_resume()
and dm_destroy() are concurrent.
Therefore, cancelling timer again in dm_integrity_dtr().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-modules
kernel-debug-modules-extra
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix
Wiz
CVE-2026-23067 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23067 [MEDIUM] CVE-2026-23067 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23067 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommu/io-pgtable-arm: fix size_t signedness bug in unmap path
__arm_lpae_unmap() returns size_t but was returning -ENOENT (negative
error code) when encountering an unmapped PTE. Since size_t is unsigned,
-ENOENT (typically -2) becomes a huge positive value (0xFFFFFFFFFFFFFFFE
on 64-bit systems).
This corrupted value propagates through the call chain:
__arm_lpae_unmap() returns -ENOENT as size_t
-> arm_lpae_unmap_pages() returns it
-> __iommu_unmap() adds it to iova address
-> iommu_pgsize() triggers BUG_ON due to corrupted iova
This can cause IOVA address overflow in __iommu_unmap() loop and
trigger BUG_ON in iommu_pgsize() from invalid address a
Wiz
CVE-2026-22996 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22996 [MEDIUM] CVE-2026-22996 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22996 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Don't store mlx5e_priv in mlx5e_dev devlink priv
mlx5e_priv is an unstable structure that can be memset(0) if profile
attaching fails, mlx5e_priv in mlx5e_dev devlink private is used to
reference the netdev and mdev associated with that struct. Instead,
store netdev directly into mlx5e_dev and get mdev from the containing
mlx5_adev aux device structure.
This fixes a kernel oops in mlx5e_remove when switchdev mode fails due
to change profile failure.
$ devlink dev eswitch set pci/0000:00:03.0 mode switchdev
Error: mlx5_core: Failed setting eswitch to offloads.
dmesg:
workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR
ml
Wiz
CVE-2026-23402 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23402 CVE-2026-23402 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23402 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: x86/mmu: Only WARN in direct MMUs when overwriting shadow-present SPTE
Adjust KVM's sanity check against overwriting a shadow-present SPTE with a
another SPTE with a different target PFN to only apply to direct MMUs,
i.e. only to MMUs without shadowed gPTEs. While it's impossible for KVM
to overwrite a shadow-present SPTE in response to a guest write, writes
from outside the scope of KVM, e.g. from host userspace, aren't detected
by KVM's write tracking and so can break KVM's shadow paging rules.
------------[ cut here ]------------
pfn != spte_to_pfn(*sptep)
WARNING: arch/x86/kvm/mmu/mmu.c:3069 at mmu_set_spte+0x1e4/0x440 [kvm], CPU#0: vmx_ep
Wiz
CVE-2023-54099 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54099 CVE-2023-54099 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54099 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: Protect reconfiguration of sb read-write from racing writes
The reconfigure / remount code takes a lot of effort to protect
filesystem's reconfiguration code from racing writes on remounting
read-only. However during remounting read-only filesystem to read-write
mode userspace writes can start immediately once we clear SB_RDONLY
flag. This is inconvenient for example for ext4 because we need to do
some writes to the filesystem (such as preparation of quota files)
before we can take userspace writes so we are clearing SB_RDONLY flag
before we are fully ready to accept userpace writes and syzbot has found
a way to exploit this [1]. Also as far as
Wiz
CVE-2026-23074 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23074 [HIGH] CVE-2026-23074 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23074 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: Enforce that teql can only be used as root qdisc
Design intent of teql is that it is only supposed to be used as root qdisc.
We need to check for that constraint.
Although not important, I will describe the scenario that unearthed this
issue for the curious.
GangMin Kim [email protected] managed to concot a scenario as follows:
ROOT qdisc 1:0 (QFQ)
├── class 1:1 (weight=15, lmax=16384) netem with delay 6.4s
└── class 1:2 (weight=1, lmax=1514) teql
GangMin sends a packet which is enqueued to 1:1 (netem).
Any invocation of dequeue by QFQ from this class will not return a packet
until after 6.4s. In the meantime, a second packet is se
Wiz
CVE-2026-23244 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23244 CVE-2026-23244 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23244 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme: fix memory allocation in nvme_pr_read_keys()
nvme_pr_read_keys() takes num_keys from userspace and uses it to
calculate the allocation size for rse via struct_size(). The upper
limit is PR_KEYS_MAX (64K).
A malicious or buggy userspace can pass a large num_keys value that
results in a 4MB allocation attempt at most, causing a warning in
the page allocator when the order exceeds MAX_PAGE_ORDER.
To fix this, use kvzalloc() instead of kzalloc().
This bug has the same reasoning and fix with the patch below: https://lore.kernel.org/linux-block/[email protected]/
Warning log:
WARNING: mm/page_alloc.c:5216 at __alloc_
Wiz
CVE-2026-23057 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23057 CVE-2026-23057 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23057 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vsock/virtio: Coalesce only linear skb
vsock/virtio common tries to coalesce buffers in rx queue: if a linear skb
(with a spare tail room) is followed by a small skb (length limited by
GOOD_COPY_LEN = 128), an attempt is made to join them.
Since the introduction of MSG_ZEROCOPY support, assumption that a small skb
will always be linear is incorrect. In the zerocopy case, data is lost and
the linear skb is appended with uninitialized kernel memory.
Of all 3 supported virtio-based transports, only loopback-transport is
affected. G2H virtio-transport rx queue operates on explicitly linear skbs;
see virtio_vsock_alloc_linear_skb() in virtio_vsock_rx_f
Wiz
CVE-2022-50814 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50814 CVE-2022-50814 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50814 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: hisilicon/zip - fix mismatch in get/set sgl_sge_nr
KASAN reported this Bug:
[17619.659757] BUG: KASAN: global-out-of-bounds in param_get_int+0x34/0x60
[17619.673193] Read of size 4 at addr fffff01332d7ed00 by task read_all/1507958
...
[17619.698934] The buggy address belongs to the variable:
[17619.708371] sgl_sge_nr+0x0/0xffffffffffffa300 [hisi_zip]
There is a mismatch in hisi_zip when get/set the variable sgl_sge_nr.
The type of sgl_sge_nr is u16, and get/set sgl_sge_nr by
param_get/set_int.
Replacing param_get/set_int to param_get/set_ushort can fix this bug.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technolog
Wiz
CVE-2026-23383 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23383 [HIGH] CVE-2026-23383 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23383 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf, arm64: Force 8-byte alignment for JIT buffer to prevent atomic tearing
struct bpf_plt contains a u64 target field. Currently, the BPF JIT
allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT
buffer.
Because the base address of the JIT buffer can be 4-byte aligned (e.g.,
ending in 0x4 or 0xc), the relative padding logic in build_plt() fails
to ensure that target lands on an 8-byte boundary.
This leads to two issues:
UBSAN reports misaligned-access warnings when dereferencing the
structure.
More critically, target is updated concurrently via WRITE_ONCE() in bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64, 64-b
Wiz
CVE-2023-54183 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54183 CVE-2023-54183 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54183 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: v4l2-core: Fix a potential resource leak in v4l2_fwnode_parse_link()
If fwnode_graph_get_remote_endpoint() fails, 'fwnode' is known to be NULL,
so fwnode_handle_put() is a no-op.
Release the reference taken from a previous fwnode_graph_get_port_parent()
call instead.
Also handle fwnode_graph_get_port_parent() failures.
In order to fix these issues, add an error handling path to the function
and the needed gotos.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabilit
Wiz
CVE-2023-54158 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54158 CVE-2023-54158 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54158 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: don't free qgroup space unless specified
Boris noticed in his simple quotas testing that he was getting a leak
with Sweet Tea's change to subvol create that stopped doing a
transaction commit. This was just a side effect of that change.
In the delayed inode code we have an optimization that will free extra
reservations if we think we can pack a dir item into an already modified
leaf. Previously this wouldn't be triggered in the subvolume create
case because we'd commit the transaction, it was still possible but
much harder to trigger. It could actually be triggered if we did a
mkdir && subvol create with qgroups enabled.
This occurs because
Wiz
CVE-2025-68736 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68736 CVE-2025-68736 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68736 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
landlock: Fix handling of disconnected directories
Disconnected files or directories can appear when they are visible and
opened from a bind mount, but have been renamed or moved from the source
of the bind mount in a way that makes them inaccessible from the mount
point (i.e. out of scope).
Previously, access rights tied to files or directories opened through a
disconnected directory were collected by walking the related hierarchy
down to the root of the filesystem, without taking into account the
mount point because it couldn't be found. This could lead to
inconsistent access results, potential access right widening, and
hard-to-debug renames, es
Wiz
CVE-2023-53821 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53821 CVE-2023-53821 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53821 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ip6_vti: fix slab-use-after-free in decode_session6
When ipv6_vti device is set to the qdisc of the sfb type, the cb field
of the sent skb may be modified during enqueuing. Then,
slab-use-after-free may occur when ipv6_vti device sends IPv6 packets.
The stack information is as follows:
BUG: KASAN: slab-use-after-free in decode_session6+0x103f/0x1890
Read of size 1 at addr ffff88802e08edc2 by task swapper/0/0
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.4.0-next-20230707-00001-g84e2cad7f979 #410
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014
Call Trace: dump_stack_lvl+0xd9/0x150
print_address_description.constpro
Wiz
CVE-2023-54053 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54053 CVE-2023-54053 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54053 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: iwlwifi: pcie: fix possible NULL pointer dereference
It is possible that iwl_pci_probe() will fail and free the trans,
then afterwards iwl_pci_remove() will be called and crash by trying
to access trans which is already freed, fix it.
iwlwifi 0000:01:00.0: Detected crf-id 0xa5a5a5a2, cnv-id 0xa5a5a5a2
wfpm id 0xa5a5a5a2
iwlwifi 0000:01:00.0: Can't find a correct rfid for crf id 0x5a2
...
BUG: kernel NULL pointer dereference, address: 0000000000000028
...
RIP: 0010:iwl_pci_remove+0x12/0x30 [iwlwifi]
pci_device_remove+0x3e/0xb0
device_release_driver_internal+0x103/0x1f0
driver_detach+0x4c/0x90
bus_remove_driver+0x5c/0xd0
driver_unregister+0x31/
Wiz
CVE-2025-68249 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68249 CVE-2025-68249 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68249 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
most: usb: hdm_probe: Fix calling put_device() before device initialization
The early error path in hdm_probe() can jump to err_free_mdev before
&mdev->dev has been initialized with device_initialize(). Calling
put_device(&mdev->dev) there triggers a device core WARN and ends up
invoking kref_put(&kobj->kref, kobject_release) on an uninitialized
kobject.
In this path the private struct was only kmalloc'ed and the intended
release is effectively kfree(mdev) anyway, so free it directly instead
of calling put_device() on an uninitialized device.
This removes the WARNING and fixes the pre-initialization error path.
Source : NVD
Published December 16
Wiz
CVE-2025-71184 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71184 [MEDIUM] CVE-2025-71184 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71184 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix NULL dereference on root when tracing inode eviction
When evicting an inode the first thing we do is to setup tracing for it,
which implies fetching the root's id. But in btrfs_evict_inode() the
root might be NULL, as implied in the next check that we do in
btrfs_evict_inode().
Hence, we either should set the ->root_objectid to 0 in case the root is
NULL, or we move tracing setup after checking that the root is not
NULL. Setting the rootid to 0 at least gives us the possibility to trace
this call even in the case when the root is NULL, so that's the solution
taken here.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity
Wiz
CVE-2023-53840 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53840 CVE-2023-53840 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53840 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: early: xhci-dbc: Fix a potential out-of-bound memory access
If xdbc_bulk_write() fails, the values in 'buf' can be anything. So the
string is not guaranteed to be NULL terminated when xdbc_trace() is called.
Reserve an extra byte, which will be zeroed automatically because 'buf' is
a static variable, in order to avoid troubles, should it happen.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected pa
Wiz
CVE-2026-22986 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-22986 [MEDIUM] CVE-2026-22986 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22986 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gpiolib: fix race condition for gdev->srcu
If two drivers were calling gpiochip_add_data_with_key(), one may be
traversing the srcu-protected list in gpio_name_to_desc(), meanwhile
other has just added its gdev in gpiodev_add_to_list_unlocked().
This creates a non-mutexed and non-protected timeframe, when one
instance is dereferencing and using &gdev->srcu, before the other
has initialized it, resulting in crash:
[ 4.935481] Unable to handle kernel paging request at virtual address ffff800272bcc000
[ 4.943396] Mem abort info:
[ 4.943400] ESR = 0x0000000096000005
[ 4.943403] EC = 0x25: DABT (current EL), IL = 32 bits
[ 4.943407] SET = 0, FnV = 0
[ 4
Wiz
CVE-2025-71265 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71265 CVE-2025-71265 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71265 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: ntfs3: fix infinite loop in attr_load_runs_range on inconsistent metadata
We found an infinite loop bug in the ntfs3 file system that can lead to a
Denial-of-Service (DoS) condition.
A malformed NTFS image can cause an infinite loop when an attribute header
indicates an empty run list, while directory entries reference it as
containing actual data. In NTFS, setting evcn=-1 with svcn=0 is a valid way
to represent an empty run list, and run_unpack() correctly handles this by
checking if evcn + 1 equals svcn and returning early without parsing any run
data. However, this creates a problem when there is metadata inconsistency,
where the attribute h
Wiz
CVE-2025-68330 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68330 CVE-2025-68330 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68330 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iio: accel: bmc150: Fix irq assumption regression
The code in bmc150-accel-core.c unconditionally calls
bmc150_accel_set_interrupt() in the iio_buffer_setup_ops,
such as on the runtime PM resume path giving a kernel
splat like this if the device has no interrupts:
Unable to handle kernel NULL pointer dereference at virtual
address 00000001 when read
PC is at bmc150_accel_set_interrupt+0x98/0x194
LR is at __pm_runtime_resume+0x5c/0x64
(...)
Call trace:
bmc150_accel_set_interrupt from bmc150_accel_buffer_postenable+0x40/0x108
bmc150_accel_buffer_postenable from __iio_update_buffers+0xbe0/0xcbc
__iio_update_buffers from enable_store+0x84/0xc8
enable_
Wiz
CVE-2026-23336 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23336 [HIGH] CVE-2026-23336 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23336 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()
There is a use-after-free error in cfg80211_shutdown_all_interfaces found
by syzkaller:
BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace: dump_stack_lvl+0x116/0x1f0
print_report+0xcd/0x630
kasan_report+0xe0/0x110
cfg80211_shutdown_all_interfaces+0x213/0x220
cfg80211_rfkill_block
Wiz
CVE-2026-23382 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23382 CVE-2026-23382 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23382 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them
In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at
raw event handle"), we handle the fact that raw event callbacks
can happen even for a HID device that has not been "claimed" causing a
crash if a broken device were attempted to be connected to the system.
Fix up the remaining in-tree HID drivers that forgot to add this same
check to resolve the same issue.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release
Wiz
CVE-2026-23099 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23099 [HIGH] CVE-2026-23099 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23099 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bonding: limit BOND_MODE_8023AD to Ethernet devices
BOND_MODE_8023AD makes sense for ARPHRD_ETHER only.
syzbot reported:
BUG: KASAN: global-out-of-bounds in __hw_addr_create net/core/dev_addr_lists.c:63 [inline]
BUG: KASAN: global-out-of-bounds in __hw_addr_add_ex+0x25d/0x760 net/core/dev_addr_lists.c:118
Read of size 16 at addr ffffffff8bf94040 by task syz.1.3580/19497
CPU: 1 UID: 0 PID: 19497 Comm: syz.1.3580 Tainted: G L syzkaller #0 PREEMPT(full)
Tainted: [L]=SOFTLOCKUP
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
Call Trace: dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
print_address_description
Wiz
CVE-2026-23145 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23145 [MEDIUM] CVE-2026-23145 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23145 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix iloc.bh leak in ext4_xattr_inode_update_ref
The error branch for ext4_xattr_inode_update_ref forget to release the
refcount for iloc.bh. Find this when review code.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-debug-devel
kernel-uek-debug-modules-extra
Sources
NVD
Container-Optimized OS Severity MEDIUM Has Fix Added
Wiz
CVE-2022-50743 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50743 CVE-2022-50743 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50743 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: Fix pcluster memleak when its block address is zero
syzkaller reported a memleak: https://syzkaller.appspot.com/bug?id=62f37ff612f0021641eda5b17f056f1668aa9aed
unreferenced object 0xffff88811009c7f8 (size 136):
...
backtrace:
[ ] z_erofs_do_read_page+0x99b/0x1740
[ ] z_erofs_readahead+0x24e/0x580
[ ] read_pages+0x86/0x3d0
...
syzkaller constructed a case: in z_erofs_register_pcluster(),
ztailpacking = false and map->m_pa = zero. This makes pcl->obj.index be
zero although pcl is not a inline pcluster.
Then following path adds refcount for grp, but the refcount won't be put
because pcl is inline.
z_erofs_readahead()
z_erofs_do_read_page() #
Wiz
CVE-2026-23467 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23467 CVE-2026-23467 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23467 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915/dmc: Fix an unlikely NULL pointer deference at probe
intel_dmc_update_dc6_allowed_count() oopses when DMC hasn't been
initialized, and dmc is thus NULL.
That would be the case when the call path is
intel_power_domains_init_hw() -> {skl,bxt,icl}_display_core_init() ->
gen9_set_dc_state() -> intel_dmc_update_dc6_allowed_count(), as
intel_power_domains_init_hw() is called before intel_dmc_init().
However, gen9_set_dc_state() calls intel_dmc_update_dc6_allowed_count()
conditionally, depending on the current and target DC states. At probe,
the target is disabled, but if DC6 is enabled, the function is called,
and an oops follows. Apparently it
Wiz
CVE-2025-71159 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71159 [HIGH] CVE-2025-71159 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71159 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix use-after-free warning in btrfs_get_or_create_delayed_node()
Previously, btrfs_get_or_create_delayed_node() set the delayed_node's
refcount before acquiring the root->delayed_nodes lock.
Commit e8513c012de7 ("btrfs: implement ref_tracker for delayed_nodes")
moved refcount_set inside the critical section, which means there is
no longer a memory barrier between setting the refcount and setting
btrfs_inode->delayed_node.
Without that barrier, the stores to node->refs and
btrfs_inode->delayed_node may become visible out of order. Another
thread can then read btrfs_inode->delayed_node and attempt to
increment a refcount that hasn't been set y
Wiz
CVE-2023-54074 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54074 CVE-2023-54074 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54074 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Use correct encap attribute during invalidation
With introduction of post action infrastructure most of the users of encap
attribute had been modified in order to obtain the correct attribute by
calling mlx5e_tc_get_encap_attr() helper instead of assuming encap action
is always on default attribute. However, the cited commit didn't modify
mlx5e_invalidate_encap() which prevents it from destroying correct modify
header action which leads to a warning [0]. Fix the issue by using correct
attribute.
[0]:
Feb 21 09:47:35 c-237-177-40-045 kernel: WARNING: CPU: 17 PID: 654 at drivers/net/ethernet/mellanox/mlx5/core/en_tc.c:684 mlx5e_tc_attach_
Wiz
CVE-2025-71101 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71101 [HIGH] CVE-2025-71101 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71101 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: hp-bioscfg: Fix out-of-bounds array access in ACPI package parsing
The hp_populate_*_elements_from_package() functions in the hp-bioscfg
driver contain out-of-bounds array access vulnerabilities.
These functions parse ACPI packages into internal data structures using
a for loop with index variable 'elem' that iterates through
enum_obj/integer_obj/order_obj/password_obj/string_obj arrays.
When processing multi-element fields like PREREQUISITES and
ENUM_POSSIBLE_VALUES, these functions read multiple consecutive array
elements using expressions like 'enum_obj[elem + reqs]' and
'enum_obj[elem + pos_values]' within nested loops.
The bug
Wiz
CVE-2026-23209 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23209 [HIGH] CVE-2026-23209 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23209 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
macvlan: fix error recovery in macvlan_common_newlink()
valis provided a nice repro to crash the kernel:
ip link add p1 type veth peer p2
ip link set address 00:00:00:00:00:20 dev p1
ip link set up dev p1
ip link set up dev p2
ip link add mv0 link p2 type macvlan mode source
ip link add invalid% link p2 type macvlan mode source macaddr add 00:00:00:00:00:20
ping -c1 -I p1 1.2.3.4
He also gave a very detailed analysis:
The issue is triggered when a new macvlan link is created with
MACVLAN_MODE_SOURCE mode and MACVLAN_MACADDR_ADD (or
MACVLAN_MACADDR_SET) parameter, lower device already has a macvlan
port and register_netdevice() called from macvl
Wiz
CVE-2023-54155 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54155 CVE-2023-54155 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54155 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: core: remove unnecessary frame_sz check in bpf_xdp_adjust_tail()
## Syzkaller reported the following issue:
Too BIG xdp->frame_sz = 131072
WARNING: CPU: 0 PID: 5020 at net/core/filter.c:4121
____bpf_xdp_adjust_tail net/core/filter.c:4121 [inline]
WARNING: CPU: 0 PID: 5020 at net/core/filter.c:4121
bpf_xdp_adjust_tail+0x466/0xa10 net/core/filter.c:4103
...
Call Trace: bpf_prog_4add87e5301a4105+0x1a/0x1c
__bpf_prog_run include/linux/filter.h:600 [inline]
bpf_prog_run_xdp include/linux/filter.h:775 [inline]
bpf_prog_run_generic_xdp+0x57e/0x11e0 net/core/dev.c:4721
netif_receive_generic_xdp net/core/dev.c:4807 [inline]
do_xdp_generic+0x35c/0x770
Wiz
CVE-2026-23166 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23166 [MEDIUM] CVE-2026-23166 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23166 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: Fix NULL pointer dereference in ice_vsi_set_napi_queues
Add NULL pointer checks in ice_vsi_set_napi_queues() to prevent crashes
during resume from suspend when rings[q_idx]->q_vector is NULL.
Tested adaptor:
60:00.0 Ethernet controller [0200]: Intel Corporation Ethernet Controller E810-XXV for SFP [8086:159b] (rev 02)
Subsystem: Intel Corporation Ethernet Network Adapter E810-XXV-2 [8086:4003]
SR-IOV state: both disabled and enabled can reproduce this issue.
kernel version: v6.18
Reproduce steps:
Boot up and execute suspend like systemctl suspend or rtcwake.
Log:
[ 231.443607] BUG: kernel NULL pointer dereference, address: 0000000000000040
Wiz
CVE-2026-23269 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23269 [HIGH] CVE-2026-23269 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23269 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
apparmor: validate DFA start states are in bounds in unpack_pdb
Start states are read from untrusted data and used as indexes into the
DFA state tables. The aa_dfa_next() function call in unpack_pdb() will
access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds
the number of states in the DFA, this results in an out-of-bound read.
BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360
Read of size 4 at addr ffff88811956fb90 by task su/1097
...
Reject policies with out-of-bounds start states during unpacking
to prevent the issue.
Source : NVD
## 7.1
Score
Published March 18, 2026
Severity HIGH
CNA Score 7.1
Affected Tech
Wiz
CVE-2025-68327 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68327 CVE-2025-68327 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68327 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: renesas_usbhs: Fix synchronous external abort on unbind
A synchronous external abort occurs on the Renesas RZ/G3S SoC if unbind is
executed after the configuration sequence described above:
modprobe usb_f_ecm
modprobe libcomposite
modprobe configfs
cd /sys/kernel/config/usb_gadget
mkdir -p g1
cd g1
echo "0x1d6b" > idVendor
echo "0x0104" > idProduct
mkdir -p strings/0x409
echo "0123456789" > strings/0x409/serialnumber
echo "Renesas." > strings/0x409/manufacturer
echo "Ethernet Gadget" > strings/0x409/product
mkdir -p functions/ecm.usb0
mkdir -p configs/c.1
mkdir -p configs/c.1/strings/0x409
echo "ECM" > configs/c.1/strings/0x409/configuration
Wiz
CVE-2023-54219 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54219 CVE-2023-54219 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54219 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Revert "IB/isert: Fix incorrect release of isert connection"
Commit: 699826f4e30a ("IB/isert: Fix incorrect release of isert connection") is
causing problems on OPA when DEVICE_REMOVAL is happening.
------------[ cut here ]------------
WARNING: CPU: 52 PID: 2117247 at drivers/infiniband/core/cq.c:359
ib_cq_pool_cleanup+0xac/0xb0 [ib_core]
Modules linked in: nfsd nfs_acl target_core_user uio tcm_fc libfc
scsi_transport_fc tcm_loop target_core_pscsi target_core_iblock target_core_file
rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs
rfkill rpcrdma rdma_ucm ib_srpt sunrpc ib_isert iscsi_target_mod target_core_mod
opa_vnic i
Wiz
CVE-2026-23312 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23312 CVE-2026-23312 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23312 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: kaweth: validate USB endpoints
The kaweth driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it. If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2023-54318 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54318 CVE-2023-54318 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54318 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/smc: use smc_lgr_list.lock to protect smc_lgr_list.list iterate in smcr_port_add
While doing smcr_port_add, there maybe linkgroup add into or delete
from smc_lgr_list.list at the same time, which may result kernel crash.
So, use smc_lgr_list.lock to protect smc_lgr_list.list iterate in
smcr_port_add.
The crash calltrace show below:
BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 0 PID: 559726 Comm: kworker/0:92 Kdump: loaded Tainted: G
Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 449e491 04/01/2014
Workqueue: events smc_ib_port_event_work [smc]
RIP: 0010:smcr_port_add+0xa6/0xf0
Wiz
CVE-2025-68358 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68358 [MEDIUM] CVE-2025-68358 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68358 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix racy bitfield write in btrfs_clear_space_info_full()
From the memory-barriers.txt document regarding memory barrier ordering
guarantees:
(*) These guarantees do not apply to bitfields, because compilers often
generate code to modify these using non-atomic read-modify-write
sequences. Do not attempt to use bitfields to synchronize parallel
algorithms.
(*) Even in cases where bitfields are protected by locks, all fields
in a given bitfield must be protected by one lock. If two fields
in a given bitfield are protected by different locks, the compiler's
non-atomic read-modify-write sequences can cause an update to one
field to corrupt the v
Wiz
CVE-2025-68357 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68357 CVE-2025-68357 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68357 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iomap: allocate s_dio_done_wq for async reads as well
Since commit 222f2c7c6d14 ("iomap: always run error completions in user
context"), read error completions are deferred to s_dio_done_wq. This
means the workqueue also needs to be allocated for async reads.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 1.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k
kernel-rt-devel
Sources
Wiz
CVE-2022-50706 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50706 CVE-2022-50706 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50706 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/ieee802154: don't warn zero-sized raw_sendmsg()
syzbot is hitting skb_assert_len() warning at __dev_queue_xmit() [1],
for PF_IEEE802154 socket's zero-sized raw_sendmsg() request is hitting
__dev_queue_xmit() with skb->len == 0.
Since PF_IEEE802154 socket's zero-sized raw_sendmsg() request was
able to return 0, don't call __dev_queue_xmit() if packet length is 0.
#include
#include
## int main(int argc, char *argv[])
{
struct sockaddr_in addr = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_LOOPBACK) };
struct iovec iov = { };
struct msghdr hdr = { .msg_name = &addr, .msg_namelen = sizeof(addr), .msg_iov = &iov, .msg_iovlen = 1 };
se
Wiz
CVE-2025-68818 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68818 CVE-2025-68818 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68818 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: Revert "scsi: qla2xxx: Perform lockless command completion in abort path"
This reverts commit 0367076b0817d5c75dfb83001ce7ce5c64d803a9.
The commit being reverted added code to __qla2x00_abort_all_cmds() to
call sp->done() without holding a spinlock. But unlike the older code
below it, this new code failed to check sp->cmd_type and just assumed
TYPE_SRB, which results in a jump to an invalid pointer in target-mode
with TYPE_TGT_CMD:
qla2xxx [0000:65:00.0]-d034:8: qla24xx_do_nack_work create sess success
0000000009f7a79b
qla2xxx [0000:65:00.0]-5003:8: ISP System Error - mbx1=1ff5h mbx2=10h
mbx3=0h mbx4=0h mbx5=191h mbx6=0h mbx7=0h.
qla2xxx [00
Wiz
CVE-2026-23048 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23048 CVE-2026-23048 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23048 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udp: call skb_orphan() before skb_attempt_defer_free()
Standard UDP receive path does not use skb->destructor.
But skmsg layer does use it, since it calls skb_set_owner_sk_safe()
from udp_read_skb().
This then triggers this warning in skb_attempt_defer_free():
DEBUG_NET_WARN_ON_ONCE(skb->destructor);
We must call skb_orphan() to fix this issue.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.3
Exploitation Probability (EPSS) N/A
Affected packa
Wiz
CVE-2022-50842 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50842 CVE-2022-50842 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50842 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/virtio: Check whether transferred 2D BO is shmem
Transferred 2D BO always must be a shmem BO. Add check for that to prevent
NULL dereference if userspace passes a VRAM BO.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-modules-core
linux-aws-5.4
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red H
Wiz
CVE-2026-23130 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23130 [MEDIUM] CVE-2026-23130 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23130 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath12k: fix dead lock while flushing management frames
Commit [1] converted the management transmission work item into a
wiphy work. Since a wiphy work can only run under wiphy lock
protection, a race condition happens in below scenario:
a management frame is queued for transmission.
ath12k_mac_op_flush() gets called to flush pending frames associated with the hardware (i.e, vif being NULL). Then in ath12k_mac_flush() the process waits for the transmission done.
Since wiphy lock has been taken by the flush process, the transmission work item has no chance to run, hence the dead lock.
From user view, this dead lock results in below issue:
Wiz
CVE-2026-23181 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23181 CVE-2026-23181 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23181 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: sync read disk super and set block size
When the user performs a btrfs mount, the block device is not set
correctly. The user sets the block size of the block device to 0x4000
by executing the BLKBSZSET command.
Since the block size change also changes the mapping->flags value, this
further affects the result of the mapping_min_folio_order() calculation.
Let's analyze the following two scenarios:
Scenario 1: Without executing the BLKBSZSET command, the block size is
0x1000, and mapping_min_folio_order() returns 0;
Scenario 2: After executing the BLKBSZSET command, the block size is
0x4000, and mapping_min_folio_order() returns 2.
do_read_
Wiz
CVE-2026-23093 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23093 [MEDIUM] CVE-2026-23093 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23093 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksmbd: smbd: fix dma_unmap_sg() nents
The dma_unmap_sg() functions should be called with the same nents as the
dma_map_sg(), not the value the map function returned.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-debug-modules
linux-azure-fde-6.17
Sources
NVD
Debian 11 Severity MEDIUM Has Fix Added at: Feb 11, 2026
Debian 12, 1
Wiz
CVE-2023-54184 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54184 CVE-2023-54184 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54184 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: iscsit: Free cmds before session free
Commands from recovery entries are freed after session has been closed.
That leads to use-after-free at command free or NPE with such call trace:
Time2Retain timer expired for SID: 1, cleaning up iSCSI session.
BUG: kernel NULL pointer dereference, address: 0000000000000140
RIP: 0010:sbitmap_queue_clear+0x3a/0xa0
Call Trace:
target_release_cmd_kref+0xd1/0x1f0 [target_core_mod]
transport_generic_free_cmd+0xd1/0x180 [target_core_mod]
iscsit_free_cmd+0x53/0xd0 [iscsi_target_mod]
iscsit_free_connection_recovery_entries+0x29d/0x320 [iscsi_target_mod]
iscsit_close_session+0x13a/0x140 [iscsi_target_mod]
Wiz
CVE-2023-54104 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54104 CVE-2023-54104 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54104 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mtd: rawnand: fsl_upm: Fix an off-by one test in fun_exec_op()
'op-cs' is copied in 'fun->mchip_number' which is used to access the
'mchip_offsets' and the 'rnb_gpio' arrays.
These arrays have NAND_MAX_CHIPS elements, so the index must be below this
limit.
Fix the sanity check in order to avoid the NAND_MAX_CHIPS value. This
would lead to out-of-bound accesses.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Wiz
CVE-2026-23087 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23087 [MEDIUM] CVE-2026-23087 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23087 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: xen: scsiback: Fix potential memory leak in scsiback_remove()
Memory allocated for struct vscsiblk_info in scsiback_probe() is not
freed in scsiback_remove() leading to potential memory leaks on remove,
as well as in the scsiback_probe() error paths. Fix that by freeing it
in scsiback_remove().
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and librari
Wiz
CVE-2025-68177 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68177 CVE-2025-68177 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68177 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cpufreq/longhaul: handle NULL policy in longhaul_exit
longhaul_exit() was calling cpufreq_cpu_get(0) without checking
for a NULL policy pointer. On some systems, this could lead to a
NULL dereference and a kernel warning or panic.
This patch adds a check using unlikely() and returns early if the
policy is NULL.
Bugzilla: #219962
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and librarie
Wiz
CVE-2023-54156 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54156 CVE-2023-54156 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54156 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sfc: fix crash when reading stats while NIC is resetting
efx_net_stats() (.ndo_get_stats64) can be called during an ethtool
selftest, during which time nic_data->mc_stats is NULL as the NIC has
been fini'd. In this case do not attempt to fetch the latest stats
from the hardware, else we will crash on a NULL dereference:
BUG: kernel NULL pointer dereference, address: 0000000000000038
RIP efx_nic_update_stats
abridged calltrace:
efx_ef10_update_stats_pf
efx_net_stats
dev_get_stats
dev_seq_printf_stats
Skipping the read is safe, we will simply give out stale stats.
To ensure that the free in efx_ef10_fini_nic() does not race against
efx_ef10_update_sta
Wiz
CVE-2026-23211 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23211 [MEDIUM] CVE-2026-23211 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23211 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm, swap: restore swap_space attr aviod kernel panic
commit 8b47299a411a ("mm, swap: mark swap address space ro and add context
debug check") made the swap address space read-only. It may lead to
kernel panic if arch_prepare_to_swap returns a failure under heavy memory
pressure as follows,
el1_abort+0x40/0x64
el1h_64_sync_handler+0x48/0xcc
el1h_64_sync+0x84/0x88
errseq_set+0x4c/0xb8 (P)
__filemap_set_wb_err+0x20/0xd0
shrink_folio_list+0xc20/0x11cc
evict_folios+0x1520/0x1be4
try_to_shrink_lruvec+0x27c/0x3dc
shrink_one+0x9c/0x228
shrink_node+0xb3c/0xeac
do_try_to_free_pages+0x170/0x4f0
try_to_free_pages+0x334/0x534
__alloc_pages_direct_reclaim+0x90/0
Wiz
CVE-2025-71141 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71141 [MEDIUM] CVE-2025-71141 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71141 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/tilcdc: Fix removal actions in case of failed probe
The drm_kms_helper_poll_fini() and drm_atomic_helper_shutdown() helpers
should only be called when the device has been successfully registered.
Currently, these functions are called unconditionally in tilcdc_fini(),
which causes warnings during probe deferral scenarios.
[ 7.972317] WARNING: CPU: 0 PID: 23 at drivers/gpu/drm/drm_atomic_state_helper.c:175 drm_atomic_helper_crtc_duplicate_state+0x60/0x68
...
[ 8.005820] drm_atomic_helper_crtc_duplicate_state from drm_atomic_get_crtc_state+0x68/0x108
[ 8.005858] drm_atomic_get_crtc_state from drm_atomic_helper_disable_all+0x90/0x1c8
[ 8.005885] dr
Wiz
CVE-2025-68219 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68219 CVE-2025-68219 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68219 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: fix memory leak in smb3_fs_context_parse_param error path
Add proper cleanup of ctx->source and fc->source to the
cifs_parse_mount_err error handler. This ensures that memory allocated
for the source strings is correctly freed on all error paths, matching
the cleanup already performed in the success path by
smb3_cleanup_fs_context_contents().
Pointers are also set to NULL after freeing to prevent potential
double-free issues.
This change fixes a memory leak originally detected by syzbot. The
leak occurred when processing Opt_source mount options if an error
happened after ctx->source and fc->source were successfully
allocated but before the f
Wiz
CVE-2023-53994 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53994 CVE-2023-53994 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53994 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ionic: remove WARN_ON to prevent panic_on_warn
Remove unnecessary early code development check and the WARN_ON
that it uses. The irq alloc and free paths have long been
cleaned up and this check shouldn't have stuck around so long.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uki-virt
kernel-uki-virt-addons
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec
Wiz
CVE-2023-54008 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54008 CVE-2023-54008 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54008 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
virtio_vdpa: build affinity masks conditionally
We try to build affinity mask via create_affinity_masks()
unconditionally which may lead several issues:
the affinity mask is not used for parent without affinity support
(only VDUSE support the affinity now)
the logic of create_affinity_masks() might not work for devices
other than block. For example it's not rare in the networking device
where the number of queues could exceed the number of CPUs. Such
case breaks the current affinity logic which is based on
group_cpus_evenly() who assumes the number of CPUs are not less than
the number of groups. This can trigger a warning[1]:
if (ret >= 0)
WARN_
Wiz
CVE-2026-23442 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23442 CVE-2026-23442 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23442 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: add NULL checks for idev in SRv6 paths
__in6_dev_get() can return NULL when the device has no IPv6 configuration
(e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER).
Add NULL checks for idev returned by __in6_dev_get() in both
seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL
pointer dereferences.
Source : NVD
## 5.5
Score
Published April 3, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.8
Exploitation Probability (EPSS) N/A
Affecte
Wiz
CVE-2023-54152 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54152 CVE-2023-54152 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54152 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: j1939: prevent deadlock by moving j1939_sk_errqueue()
This commit addresses a deadlock situation that can occur in certain
scenarios, such as when running data TP/ETP transfer and subscribing to
the error queue while receiving a net down event. The deadlock involves
locks in the following order:
3
j1939_session_list_lock -> active_session_list_lock
j1939_session_activate
...
j1939_sk_queue_activate_next -> sk_session_queue_lock
...
j1939_xtp_rx_eoma_one
2
j1939_sk_queue_drop_all -> sk_session_queue_lock
...
j1939_sk_netdev_event_netdown -> j1939_socks_lock
j1939_netdev_notify
1
j1939_sk_errqueue -> j1939_socks_lock
__j1939_session_cancel ->
Wiz
CVE-2023-53844 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53844 CVE-2023-53844 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53844 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/ttm: Don't leak a resource on swapout move error
If moving the bo to system for swapout failed, we were leaking
a resource. Fix.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-libbpf-static
kernel-64k
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 09, 2025
Echo Has Fix Added at: Dec 09, 2025
Red Hat 8 Severity LOW Has Fix Added at: Dec 11, 2025
Red Hat 9
Wiz
CVE-2026-23238 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23238 [MEDIUM] CVE-2026-23238 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23238 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
romfs: check sb_set_blocksize() return value
romfs_fill_super() ignores the return value of sb_set_blocksize(), which
can fail if the requested block size is incompatible with the block
device's configuration.
This can be triggered by setting a loop device's block size larger than
PAGE_SIZE using ioctl(LOOP_SET_BLOCK_SIZE, 32768), then mounting a romfs
filesystem on that device.
When sb_set_blocksize(sb, ROMBSIZE) is called with ROMBSIZE=4096 but the
device has logical_block_size=32768, bdev_validate_blocksize() fails
because the requested size is smaller than the device's logical block
size. sb_set_blocksize() returns 0 (failure), but romfs ignor
Wiz
CVE-2023-54302 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54302 CVE-2023-54302 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54302 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/irdma: Fix data race on CQP completion stats
CQP completion statistics is read lockesly in irdma_wait_event and
irdma_check_cqp_progress while it can be updated in the completion
thread irdma_sc_ccq_get_cqe_info on another CPU as KCSAN reports.
Make completion statistics an atomic variable to reflect coherent updates
to it. This will also avoid load/store tearing logic bug potentially
possible by compiler optimizations.
[77346.170861] BUG: KCSAN: data-race in irdma_handle_cqp_op [irdma] / irdma_sc_ccq_get_cqe_info [irdma]
[77346.171383] write to 0xffff8a3250b108e0 of 8 bytes by task 9544 on cpu 4:
[77346.171483] irdma_sc_ccq_get_cqe_info+0x2
Wiz
CVE-2022-50717 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50717 CVE-2022-50717 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50717 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet-tcp: add bounds check on Transfer Tag
ttag is used as an index to get cmd in nvmet_tcp_handle_h2c_data_pdu(),
add a bounds check to avoid out-of-bounds access.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-modules
kernel-zfcpdump-modules
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8 S
Wiz
CVE-2025-71111 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2025-71111 [MEDIUM] CVE-2025-71111 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71111 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hwmon: (w83791d) Convert macros to functions to avoid TOCTOU
The macro FAN_FROM_REG evaluates its arguments multiple times. When used
in lockless contexts involving shared driver data, this leads to
Time-of-Check to Time-of-Use (TOCTOU) race conditions, potentially
causing divide-by-zero errors.
Convert the macro to a static function. This guarantees that arguments
are evaluated only once (pass-by-value), preventing the race
conditions.
Additionally, in store_fan_div, move the calculation of the minimum
limit inside the update lock. This ensures that the read-modify-write
sequence operates on consistent data.
Adhere to the principle of minimal ch
Wiz
CVE-2023-54018 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54018 CVE-2023-54018 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54018 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/hdmi: Add missing check for alloc_ordered_workqueue
hdmi_hdcp.c
hdmi_hpd.c
Patchwork: https://patchwork.freedesktop.org/patch/517211/
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-raspi-5.4
kernel-default
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Ubuntu 16.04 Severity MEDIUM No Fix Added at: De
Wiz
CVE-2022-50881 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50881 CVE-2022-50881 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50881 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath9k: Fix use-after-free in ath9k_hif_usb_disconnect()
This patch fixes a use-after-free in ath9k that occurs in
ath9k_hif_usb_disconnect() when ath9k_destroy_wmi() is trying to access
'drv_priv' that has already been freed by ieee80211_free_hw(), called by
ath9k_htc_hw_deinit(). The patch moves ath9k_destroy_wmi() before
ieee80211_free_hw(). Note that urbs from the driver should be killed
before freeing 'wmi' with ath9k_destroy_wmi() as their callbacks will
access 'wmi'.
Found by a modified version of syzkaller.
BUG: KASAN: use-after-free in ath9k_destroy_wmi+0x38/0x40
Read of size 8 at addr ffff8881069132a0 by task kworker/0:1/7
CPU: 0 P
Wiz
CVE-2022-50884 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50884 CVE-2022-50884 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50884 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm: Prevent drm_copy_field() to attempt copying a NULL pointer
There are some struct drm_driver fields that are required by drivers since
drm_copy_field() attempts to copy them to user-space via DRM_IOCTL_VERSION.
But it can be possible that a driver has a bug and did not set some of the
fields, which leads to drm_copy_field() attempting to copy a NULL pointer:
[ +10.395966] Unable to handle kernel access to user memory outside uaccess routines at virtual address 0000000000000000
[ +0.010955] Mem abort info:
[ +0.002835] ESR = 0x0000000096000004
[ +0.003872] EC = 0x25: DABT (current EL), IL = 32 bits
[ +0.005395] SET = 0, FnV = 0
[ +0.003113] EA
Wiz
CVE-2026-31399 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31399 CVE-2026-31399 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31399 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvdimm/bus: Fix potential use after free in asynchronous initialization
Dingisoul with KASAN reports a use after free if device_add() fails in
nd_async_device_register().
Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while
scheduling async init") correctly added a reference on the parent device
to be held until asynchronous initialization was complete. However, if
device_add() results in an allocation failure the ref count of the
device drops to 0 prior to the parent pointer being accessed. Thus
resulting in use after free.
The bug bot AI correctly identified the fix. Save a reference to the
parent pointer to be used to drop the parent
Wiz
CVE-2023-54028 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54028 CVE-2023-54028 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54028 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"
In the function rxe_create_qp(), rxe_qp_from_init() is called to
initialize qp, internally things like rxe_init_task are not setup until
rxe_qp_init_req().
If an error occurred before this point then the unwind will call
rxe_cleanup() and eventually to rxe_qp_do_cleanup()/rxe_cleanup_task()
which will oops when trying to access the uninitialized spinlock.
If rxe_init_task is not executed, rxe_cleanup_task will not be called.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV
Wiz
CVE-2026-23167 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23167 [MEDIUM] CVE-2026-23167 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23167 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfc: nci: Fix race between rfkill and nci_unregister_device().
syzbot reported the splat below [0] without a repro.
It indicates that struct nci_dev.cmd_wq had been destroyed before
nci_close_device() was called via rfkill.
nci_dev.cmd_wq is only destroyed in nci_unregister_device(), which
(I think) was called from virtual_ncidev_close() when syzbot close()d
an fd of virtual_ncidev.
The problem is that nci_unregister_device() destroys nci_dev.cmd_wq
first and then calls nfc_unregister_device(), which removes the
device from rfkill by rfkill_unregister().
So, the device is still visible via rfkill even after nci_dev.cmd_wq
is destroyed.
Let's un
Wiz
CVE-2026-23392 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23392 [HIGH] CVE-2026-23392 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23392 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: release flowtable after rcu grace period on error
Call synchronize_rcu() after unregistering the hooks from error path,
since a hook that already refers to this flowtable can be already
registered, exposing this flowtable to packet path and nfnetlink_hook
control plane.
This error path is rare, it should only happen by reaching the maximum
number hooks or by failing to set up to hardware offload, just call
synchronize_rcu().
There is a check for already used device hooks by different flowtable
that could result in EEXIST at this late stage. The hook parser can be
updated to perform this check earlier to this error path really
Wiz
CVE-2026-23310 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23310 CVE-2026-23310 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23310 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded
bond_option_mode_set() already rejects mode changes that would make a
loaded XDP program incompatible via bond_xdp_check(). However,
bond_option_xmit_hash_policy_set() has no such guard.
For 802.3ad and balance-xor modes, bond_xdp_check() returns false when
xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually
absent due to hardware offload. This means a user can:
Attach a native XDP program to a bond in 802.3ad/balance-xor mode
with a compatible xmit_hash_policy (e.g. layer2+3).
Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.
This leaves
Wiz
CVE-2026-23361 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23361 CVE-2026-23361 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23361 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry
Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X
interrupt to the host using a writel(), which generates a PCI posted write
transaction. There's no completion for posted writes, so the writel() may
return before the PCI write completes. dw_pcie_ep_raise_msix_irq() also
unmaps the outbound ATU entry used for the PCI write, so the write races
with the unmap.
If the PCI write loses the race with the ATU unmap, the write may corrupt
host memory or cause IOMMU errors, e.g., these when running fio with a
larger queue depth against nvmet-pci-epf:
arm-smmu-v3 fc900000.iommu:
Wiz
CVE-2025-40346 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40346 CVE-2025-40346 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40346 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arch_topology: Fix incorrect error check in topology_parse_cpu_capacity()
Fix incorrect use of PTR_ERR_OR_ZERO() in topology_parse_cpu_capacity()
which causes the code to proceed with NULL clock pointers. The current
logic uses !PTR_ERR_OR_ZERO(cpu_clk) which evaluates to true for both
valid pointers and NULL, leading to potential NULL pointer dereference
in clk_get_rate().
Per include/linux/err.h documentation, PTR_ERR_OR_ZERO(ptr) returns:
"The error code within @ptr if it is an error pointer; 0 otherwise."
This means PTR_ERR_OR_ZERO() returns 0 for both valid pointers AND NULL
pointers. Therefore !PTR_ERR_OR_ZERO(cpu_clk) evaluates to true (pro
Wiz
CVE-2026-23271 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23271 [HIGH] CVE-2026-23271 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23271 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf: Fix __perf_event_overflow() vs perf_remove_from_context() race
Make sure that __perf_event_overflow() runs with IRQs disabled for all
possible callchains. Specifically the software events can end up running
it with only preemption disabled.
This opens up a race vs perf_event_exit_event() and friends that will go
and free various things the overflow path expects to be present, like
the BPF program.
Source : NVD
## 7.8
Score
Published March 20, 2026
Severity HIGH
CNA Score 7.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2022-50722 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50722 CVE-2022-50722 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50722 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: ipu3-imgu: Fix NULL pointer dereference in active selection access
What the IMGU driver did was that it first acquired the pointers to active
and try V4L2 subdev state, and only then figured out which one to use.
The problem with that approach and a later patch (see Fixes: tag) is that
as sd_state argument to v4l2_subdev_get_try_crop() et al is NULL, there is
now an attempt to dereference that.
Fix this.
Also rewrap lines a little.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exp
Wiz
CVE-2026-23005 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23005 [MEDIUM] CVE-2026-23005 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23005 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/fpu: Clear XSTATE_BV[i] in guest XSAVE state whenever XFD[i]=1
When loading guest XSAVE state via KVM_SET_XSAVE, and when updating XFD in
response to a guest WRMSR, clear XFD-disabled features in the saved (or to
be restored) XSTATE_BV to ensure KVM doesn't attempt to load state for
features that are disabled via the guest's XFD. Because the kernel
executes XRSTOR with the guest's XFD, saving XSTATE_BV[i]=1 with XFD[i]=1
will cause XRSTOR to #NM and panic the kernel.
E.g. if fpu_update_guest_xfd() sets XFD without clearing XSTATE_BV:
------------[ cut here ]------------
WARNING: arch/x86/kernel/traps.c:1524 at exc_device_not_available+0x101/0x
Wiz
CVE-2026-23138 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23138 [MEDIUM] CVE-2026-23138 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23138 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Add recursion protection in kernel stack trace recording
A bug was reported about an infinite recursion caused by tracing the rcu
events with the kernel stack trace trigger enabled. The stack trace code
called back into RCU which then called the stack trace again.
Expand the ftrace recursion protection to add a set of bits to protect
events from recursion. Each bit represents the context that the event is
in (normal, softirq, interrupt and NMI).
Have the stack trace code use the interrupt context to protect against
recursion.
Note, the bug showed an issue in both the RCU code as well as the tracing
stacktrace code. This only handles the
Wiz
CVE-2025-68254 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68254 CVE-2025-68254 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68254 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8723bs: fix out-of-bounds read in OnBeacon ESR IE parsing
The Extended Supported Rates (ESR) IE handling in OnBeacon accessed
*(p + 1 + ielen) and *(p + 2 + ielen) without verifying that these
offsets lie within the received frame buffer. A malformed beacon with
an ESR IE positioned at the end of the buffer could cause an
out-of-bounds read, potentially triggering a kernel panic.
Add a boundary check to ensure that the ESR IE body and the subsequent
bytes are within the limits of the frame before attempting to access
them.
This prevents OOB reads caused by malformed beacon frames.
Source : NVD
## 7.1
Score
Published December 16,
Wiz
CVE-2026-23146 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23146 [MEDIUM] CVE-2026-23146 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23146 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_uart: fix null-ptr-deref in hci_uart_write_work
hci_uart_set_proto() sets HCI_UART_PROTO_INIT before calling
hci_uart_register_dev(), which calls proto->open() to initialize
hu->priv. However, if a TTY write wakeup occurs during this window,
hci_uart_tx_wakeup() may schedule write_work before hu->priv is
initialized, leading to a NULL pointer dereference in
hci_uart_write_work() when proto->dequeue() accesses hu->priv.
The race condition is:
CPU0 CPU1
hci_uart_set_proto()
set_bit(HCI_UART_PROTO_INIT)
hci_uart_register_dev()
tty write wakeup
hci_uart_tty_wakeup()
hci_uart_tx_wakeup()
schedule_work(&hu->write_work)
proto->open(hu)
//
Wiz
CVE-2023-54130 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54130 CVE-2023-54130 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54130 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfs/hfsplus: avoid WARN_ON() for sanity check, use proper error handling
Commit 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") fixed
a build warning by turning a comment into a WARN_ON(), but it turns out
that syzbot then complains because it can trigger said warning with a
corrupted hfs image.
The warning actually does warn about a bad situation, but we are much
better off just handling it as the error it is. So rather than warn
about us doing bad things, stop doing the bad things and return -EIO.
While at it, also fix a memory leak that was introduced by an earlier
fix for a similar syzbot warning situation, and add a check for one c
Wiz
CVE-2026-23377 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23377 CVE-2026-23377 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23377 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: change XDP RxQ frag_size from DMA write length to xdp.frame_sz
The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buff size instead
of DMA write size. Different assumptions in ice driver configuration lead
to negative tailroom.
This allows to trigger kernel panic, when using
XDP_ADJUST_TAIL_GROW_MULTI_BUFF xskxceiver test and changing packet size to
6912 and the requested offset to a huge value, e.g.
XSK_UMEM__MAX_FRAME_SIZE * 100.
Due to other quirks of the ZC configuration in ice, panic is not observed
in ZC mode, but tailroom growing still fails when it should not.
Use fill queue bu
Wiz
CVE-2026-23160 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23160 [MEDIUM] CVE-2026-23160 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23160 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
octeon_ep: Fix memory leak in octep_device_setup()
In octep_device_setup(), if octep_ctrl_net_init() fails, the function
returns directly without unmapping the mapped resources and freeing the
allocated configuration memory.
Fix this by jumping to the unsupported_dev label, which performs the
necessary cleanup. This aligns with the error handling logic of other
paths in this function.
Compile tested only. Issue found using a prototype static analysis tool
and code review.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KE
Wiz
CVE-2026-23419 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23419 CVE-2026-23419 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23419 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/rds: Fix circular locking dependency in rds_tcp_tune
syzbot reported a circular locking dependency in rds_tcp_tune() where
sk_net_refcnt_upgrade() is called while holding the socket lock:
## ======================================================
WARNING: possible circular locking dependency detected
kworker/u10:8/15040 is trying to acquire lock:
ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0},
at: __kmalloc_cache_noprof+0x4b/0x6f0
but task is already holding lock:
ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0},
at: rds_tcp_tune+0xd7/0x930
The issue occurs because sk_net_refcnt_upgrade() performs memory
allocation (via get_net_track() -> ref_t
Wiz
CVE-2023-54205 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54205 CVE-2023-54205 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54205 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pinctrl: stm32: Fix refcount leak in stm32_pctrl_get_irq_domain
of_irq_find_parent() returns a node pointer with refcount incremented,
We should use of_node_put() on it when not needed anymore.
Add missing of_node_put() to avoid refcount leak.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
ocfs2-kmp-default
kernel-devel-rt
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added
Wiz
CVE-2026-23472 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23472 CVE-2026-23472 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23472 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN
uart_write_room() and uart_write() behave inconsistently when
xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were
never properly initialized):
uart_write_room() returns kfifo_avail() which can be > 0
uart_write() checks xmit_buf and returns 0 if NULL
This inconsistency causes an infinite loop in drivers that rely on
tty_write_room() to determine if they can write:
while (tty_write_room(tty) > 0) {
written = tty->ops->write(...);
// written is always 0, loop never exits
}
For example, caif_serial's handle_tx() enters an infinite loop when
used with PORT_UNKNOWN serial p
Wiz
CVE-2026-23151 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23151 [MEDIUM] CVE-2026-23151 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23151 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: MGMT: Fix memory leak in set_ssp_complete
Fix memory leak in set_ssp_complete() where mgmt_pending_cmd structures
are not freed after being removed from the pending list.
Commit 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs") replaced
mgmt_pending_foreach() calls with individual command handling but missed
adding mgmt_pending_free() calls in both error and success paths of
set_ssp_complete(). Other completion functions like set_le_complete()
were fixed correctly in the same commit.
This causes a memory leak of the mgmt_pending_cmd structure and its
associated parameter data for each SSP command that completes.
Add the missing mgmt_
Wiz
CVE-2026-23332 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23332 CVE-2026-23332 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23332 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cpufreq: intel_pstate: Fix crash during turbo disable
When the system is booted with kernel command line argument "nosmt" or
"maxcpus" to limit the number of CPUs, disabling turbo via:
echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo
results in a crash:
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP PTI
...
RIP: 0010:store_no_turbo+0x100/0x1f0
...
This occurs because for_each_possible_cpu() returns CPUs even if they
are not online. For those CPUs, all_cpu_data[] will be NULL. Since
commit 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency
updates handling
Wiz
CVE-2026-23090 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23090 [MEDIUM] CVE-2026-23090 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23090 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
slimbus: core: fix device reference leak on report present
Slimbus devices can be allocated dynamically upon reception of
report-present messages.
Make sure to drop the reference taken when looking up already registered
devices.
Note that this requires taking an extra reference in case the device has
not yet been registered and has to be allocated.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Pr
Wiz
CVE-2026-23073 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23073 [HIGH] CVE-2026-23073 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23073 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rsi: Fix memory corruption due to not set vif driver data size
The struct ieee80211_vif contains trailing space for vif driver data,
when struct ieee80211_vif is allocated, the total memory size that is
allocated is sizeof(struct ieee80211_vif) + size of vif driver data.
The size of vif driver data is set by each WiFi driver as needed.
The RSI911x driver does not set vif driver data size, no trailing space
for vif driver data is therefore allocated past struct ieee80211_vif .
The RSI911x driver does however use the vif driver data to store its
vif driver data structure "struct vif_priv". An access to vif->drv_priv
leads to access out of struc
Wiz
CVE-2025-68232 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68232 CVE-2025-68232 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68232 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
veth: more robust handing of race to avoid txq getting stuck
Commit dc82a33297fc ("veth: apply qdisc backpressure on full ptr_ring to
reduce TX drops") introduced a race condition that can lead to a permanently
stalled TXQ. This was observed in production on ARM64 systems (Ampere Altra
Max).
The race occurs in veth_xmit(). The producer observes a full ptr_ring and
stops the queue (netif_tx_stop_queue()). The subsequent conditional logic,
intended to re-wake the queue if the consumer had just emptied it (if
(__ptr_ring_empty(...)) netif_tx_wake_queue()), can fail. This leads to a
"lost wakeup" where the TXQ remains stopped (QUEUE_STATE_DRV_XOFF) and
Wiz
CVE-2026-23298 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23298 CVE-2026-23298 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23298 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: ucan: Fix infinite loop from zero-length messages
If a broken ucan device gets a message with the message length field set
to 0, then the driver will loop for forever in
ucan_read_bulk_callback(), hanging the system. If the length is 0, just
skip the message and go on to the next one.
This has been fixed in the kvaser_usb driver in the past in commit
0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in
command parsers"), so there must be some broken devices out there like
this somewhere.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Ha
Wiz
CVE-2025-68366 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68366 CVE-2025-68366 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68366 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nbd: defer config unlock in nbd_genl_connect
There is one use-after-free warning when running NBD_CMD_CONNECT and
NBD_CLEAR_SOCK:
nbd_genl_connect
nbd_alloc_and_init_config // config_refs=1
nbd_start_device // config_refs=2
set NBD_RT_HAS_CONFIG_REF open nbd // config_refs=3
recv_work done // config_refs=2
NBD_CLEAR_SOCK // config_refs=1
close nbd // config_refs=0
refcount_inc -> uaf
------------[ cut here ]------------
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 24 PID: 1014 at lib/refcount.c:25 refcount_warn_saturate+0x12e/0x290
nbd_genl_connect+0x16d0/0x1ab0
genl_family_rcv_msg_doit+0x1f3/0x310
genl_rcv_msg+0x44a/0x790
The issue c
Wiz
CVE-2025-71127 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71127 [MEDIUM] CVE-2025-71127 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71127 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: Discard Beacon frames to non-broadcast address
Beacon frames are required to be sent to the broadcast address, see IEEE
Std 802.11-2020, 11.1.3.1 ("The Address 1 field of the Beacon .. frame
shall be set to the broadcast address"). A unicast Beacon frame might be
used as a targeted attack to get one of the associated STAs to do
something (e.g., using CSA to move it to another channel). As such, it
is better have strict filtering for this on the received side and
discard all Beacon frames that are sent to an unexpected address.
This is even more important for cases where beacon protection is used.
The current implementation in mac802
Wiz
CVE-2023-53845 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53845 CVE-2023-53845 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53845 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nilfs2: fix infinite loop in nilfs_mdt_get_block()
If the disk image that nilfs2 mounts is corrupted and a virtual block
address obtained by block lookup for a metadata file is invalid,
nilfs_bmap_lookup_at_level() may return the same internal return code as
-ENOENT, meaning the block does not exist in the metadata file.
This duplication of return codes confuses nilfs_mdt_get_block(), causing
it to read and create a metadata block indefinitely.
In particular, if this happens to the inode metadata file, ifile,
semaphore i_rwsem can be left held, causing task hangs in lock_mount.
Fix this issue by making nilfs_bmap_lookup_at_level() treat virtual b
Wiz
CVE-2025-68221 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68221 CVE-2025-68221 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68221 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: fix address removal logic in mptcp_pm_nl_rm_addr
Fix inverted WARN_ON_ONCE condition that prevented normal address
removal counter updates. The current code only executes decrement
logic when the counter is already 0 (abnormal state), while
normal removals (counter > 0) are ignored.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug
kernel-devel
Sources
NVD
Wiz
CVE-2023-54282 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54282 CVE-2023-54282 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54282 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: tuners: qt1010: replace BUG_ON with a regular error
BUG_ON is unnecessary here, and in addition it confuses smatch.
Replacing this with an error return help resolve this smatch
warning:
drivers/media/tuners/qt1010.c:350 qt1010_init() error: buffer overflow 'i2c_data' 34 <= 34
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 13.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt
kernel-rt-debug-core
Sources
NVD
Wiz
CVE-2022-50845 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50845 CVE-2022-50845 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50845 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix inode leak in ext4_xattr_inode_create() on an error path
There is issue as follows when do setxattr with inject fault:
[localhost]# fsck.ext4 -fn /dev/sda
e2fsck 1.46.6-rc1 (12-Sep-2022)
Pass 1: Checking inodes, blocks, and sizes
Pass 2: Checking directory structure
Pass 3: Checking directory connectivity
Pass 4: Checking reference counts
Unattached zero-length inode 15. Clear? no
Unattached inode 15
Connect to /lost+found? no
Pass 5: Checking group summary information
/dev/sda: ********** WARNING: Filesystem still has errors **********
/dev/sda: 15/655360 files (0.0% non-contiguous), 66755/2621440 blocks
This occurs in 'ext4_xattr_i
Wiz
CVE-2026-23257 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23257 CVE-2026-23257 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23257 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: liquidio: Fix off-by-one error in PF setup_nic_devices() cleanup
In setup_nic_devices(), the initialization loop jumps to the label
setup_nic_dev_free on failure. The current cleanup loop while(i--)
skip the failing index i, causing a memory leak.
Fix this by changing the loop to iterate from the current index i
down to 0.
Also, decrement i in the devlink_alloc failure path to point to the
last successfully allocated index.
Compile tested only. Issue found using code review.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Relea
Wiz
CVE-2026-23222 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23222 [HIGH] CVE-2026-23222 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23222 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: omap - Allocate OMAP_CRYPTO_FORCE_COPY scatterlists correctly
The existing allocation of scatterlists in omap_crypto_copy_sg_lists()
was allocating an array of scatterlist pointers, not scatterlist objects,
resulting in a 4x too small allocation.
Use sizeof(*new_sg) to get the correct object size.
Source : NVD
## 5.5
Score
Published February 18, 2026
Severity MEDIUM
CNA Score 7.8
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.9
Exploitation Probability (EPSS) N/A
Affected packages and
Wiz
CVE-2026-23247 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23247 CVE-2026-23247 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23247 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tcp: secure_seq: add back ports to TS offset
This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets")
tcp_tw_recycle went away in 2017.
Zhouyan Deng reported off-path TCP source port leakage via
SYN cookie side-channel that can be fixed in multiple ways.
One of them is to bring back TCP ports in TS offset randomization.
As a bonus, we perform a single siphash() computation
to provide both an ISN and a TS offset.
Source : NVD
## 6.5
Score
Published March 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N
Wiz
CVE-2023-54141 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54141 CVE-2023-54141 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54141 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: Add missing hw_ops->get_ring_selector() for IPQ5018
During sending data after clients connected, hw_ops->get_ring_selector()
will be called. But for IPQ5018, this member isn't set, and the
following NULL pointer exception will be occurred:
[ 38.840478] 8] (ath11k_dp_tx [ath11k]) from [] (ath11k_mac_op_tx+0x80/0x190 [ath11k])
[ 39.446607] [] (ath11k_mac_op_tx [ath11k]) from [] (ieee80211_handle_wake_tx_queue+0x7c/0xc0 [mac80211])
[ 39.456162] [] (ieee80211_handle_wake_tx_queue [mac80211]) from [] (ieee80211_probereq_get+0x584/0x704 [mac80211])
[ 39.467443] [] (ieee80211_probereq_get [mac80211]) from [] (ieee80211_tx_prepare_skb+0x1f8/0
Wiz
CVE-2022-50737 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50737 CVE-2022-50737 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50737 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Validate index root when initialize NTFS security
This enhances the sanity check for $SDH and $SII while initializing NTFS
security, guarantees these index root are legit.
[ 162.459513] BUG: KASAN: use-after-free in hdr_find_e.isra.0+0x10c/0x320
[ 162.460176] Read of size 2 at addr ffff8880037bca99 by task mount/243
[ 162.460851]
[ 162.461252] CPU: 0 PID: 243 Comm: mount Not tainted 6.0.0-rc7 #42
[ 162.461744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[ 162.462609] Call Trace:
[ 162.462954] [ 162.463276] dump_stack_lvl+0x49/0x63
[ 162.463822] print_report.cold+0xf5/
Wiz
CVE-2025-71189 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71189 [MEDIUM] CVE-2025-71189 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71189 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: dw: dmamux: fix OF node leak on route allocation failure
Make sure to drop the reference taken to the DMA master OF node also on
late route allocation failures.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
cluster-md-kmp-default
dtb-allwinner
Sources
NVD
Debian 11 Severity MEDIUM Has Fix Added at: Feb 11, 2026
Debian 12, 13,
Wiz
CVE-2025-68363 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68363 CVE-2025-68363 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68363 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Check skb->transport_header is set in bpf_skb_check_mtu
The bpf_skb_check_mtu helper needs to use skb->transport_header when
the BPF_MTU_CHK_SEGS flag is used:
bpf_skb_check_mtu(skb, ifindex, &mtu_len, 0, BPF_MTU_CHK_SEGS)
The transport_header is not always set. There is a WARN_ON_ONCE
report when CONFIG_DEBUG_NET is enabled + skb->gso_size is set +
bpf_prog_test_run is used:
WARNING: CPU: 1 PID: 2216 at ./include/linux/skbuff.h:3071
skb_gso_validate_network_len
bpf_skb_check_mtu
bpf_prog_3920e25740a41171_tc_chk_segs_flag # A test in the next patch
bpf_test_run
bpf_prog_test_run_skb
For a normal ingress skb (not test_run), skb_reset_transpo
Wiz
CVE-2025-68778 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68778 CVE-2025-68778 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68778 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: don't log conflicting inode if it's a dir moved in the current transaction
We can't log a conflicting inode if it's a directory and it was moved
from one parent directory to another parent directory in the current
transaction, as this can result an attempt to have a directory with
two hard links during log replay, one for the old parent directory and
another for the new parent directory.
The following scenario triggers that issue:
We have directories "dir1" and "dir2" created in a past transaction.
Directory "dir1" has inode A as its parent directory;
We move "dir1" to some other directory;
We create a file with the name "dir1" in directo
Wiz
CVE-2022-50779 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50779 CVE-2022-50779 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50779 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
orangefs: Fix kmemleak in orangefs_prepare_debugfs_help_string()
When insert and remove the orangefs module, then debug_help_string will
be leaked:
unreferenced object 0xffff8881652ba000 (size 4096):
comm "insmod", pid 1701, jiffies 4294893639 (age 13218.530s)
hex dump (first 32 bytes):
43 6c 69 65 6e 74 20 44 65 62 75 67 20 4b 65 79 Client Debug Key
77 6f 72 64 73 20 61 72 65 20 75 6e 6b 6e 6f 77 words are unknow
backtrace:
[] kmalloc_trace+0x27/0xa0
[] orangefs_prepare_debugfs_help_string+0x5e/0x480 [orangefs]
[] _sub_I_65535_1+0x57/0xf70 [crc_itu_t]
[] do_one_initcall+0x87/0x2a0
[] do_init_module+0xdf/0x320
[] load_module+0x2f98/0x3330
[] __do_s
Wiz
CVE-2026-23462 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23462 CVE-2026-23462 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23462 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: HIDP: Fix possible UAF
This fixes the following trace caused by not dropping l2cap_conn
reference when user->remove callback is called:
[ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00
[ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy)
[ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[ 97.809947] Call Trace:
[ 97.809954] [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122)
[ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808)
[ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:182
Wiz
CVE-2025-68241 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68241 CVE-2025-68241 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68241 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv4: route: Prevent rt_bind_exception() from rebinding stale fnhe
The sit driver's packet transmission path calls: sit_tunnel_xmit() ->
update_or_create_fnhe(), which lead to fnhe_remove_oldest() being called
to delete entries exceeding FNHE_RECLAIM_DEPTH+random.
The race window is between fnhe_remove_oldest() selecting fnheX for
deletion and the subsequent kfree_rcu(). During this time, the
concurrent path's __mkroute_output() -> find_exception() can fetch the
soon-to-be-deleted fnheX, and rt_bind_exception() then binds it with a
new dst using a dst_hold(). When the original fnheX is freed via RCU,
the dst reference remains permanently leaked.
C
Wiz
CVE-2022-50838 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50838 CVE-2022-50838 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50838 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: stream: purge sk_error_queue in sk_stream_kill_queues()
Changheon Lee reported TCP socket leaks, with a nice repro.
It seems we leak TCP sockets with the following sequence:
SOF_TIMESTAMPING_TX_ACK is enabled on the socket.
Each ACK will cook an skb put in error queue, from __skb_tstamp_tx().
__skb_tstamp_tx() is using skb_clone(), unless
SOF_TIMESTAMPING_OPT_TSONLY was also requested.
If the application is also using MSG_ZEROCOPY, then we put in the
error queue cloned skbs that had a struct ubuf_info attached to them.
Whenever an struct ubuf_info is allocated, sock_zerocopy_alloc()
does a sock_hold().
As long as the cloned skbs are still
Wiz
CVE-2026-33065 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 6.9
CVE-2026-33065 [MEDIUM] CVE-2026-33065 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-33065 :
Linux Ubuntu vulnerability analysis and mitigation
Free5GC is an open-source Linux Foundation project for 5th generation (5G) mobile core networks. In versions prior to 1.4.2, the UDM incorrectly converts a downstream 400 Bad Request (from UDR) into a 500 Internal Server Error when handling DELETE requests with an empty supi path parameter. This leaks internal error handling behavior and makes it difficult for clients to distinguish between client-side errors and server-side failures. When a client sends a DELETE request with an empty supi (e.g., double slashes // in URL path), the UDM forwards the malformed request to UDR, which correctly returns 400. However, UDM propagates this as 500 SYSTEM_FAILURE instead of returning the appropriate 400 error to the client. This
Wiz
CVE-2026-23113 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23113 [MEDIUM] CVE-2026-23113 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23113 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/io-wq: check IO_WQ_BIT_EXIT inside work run loop
Currently this is checked before running the pending work. Normally this
is quite fine, as work items either end up blocking (which will create a
new worker for other items), or they complete fairly quickly. But syzbot
reports an issue where io-wq takes seemingly forever to exit, and with a
bit of debugging, this turns out to be because it queues a bunch of big
(2GB - 4096b) reads with a /dev/msr* file. Since this file type doesn't
support ->read_iter(), loop_rw_iter() ends up handling them. Each read
returns 16MB of data read, which takes 20 (!!) seconds. With a bunch of
these pending, proce
Wiz
CVE-2025-68194 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68194 CVE-2025-68194 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68194 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: imon: make send_packet() more robust
syzbot is reporting that imon has three problems which result in
hung tasks due to forever holding device lock [1].
First problem is that when usb_rx_callback_intf0() once got -EPROTO error
after ictx->dev_present_intf0 became true, usb_rx_callback_intf0()
resubmits urb after printk(), and resubmitted urb causes
usb_rx_callback_intf0() to again get -EPROTO error. This results in
printk() flooding (RCU stalls).
Alan Stern commented [2] that
In theory it's okay to resubmit if the driver has a robust
error-recovery scheme (such as giving up after some fixed limit on the
number of errors or after some fixed
Wiz
CVE-2022-50748 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50748 CVE-2022-50748 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50748 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipc: mqueue: fix possible memory leak in init_mqueue_fs()
commit db7cfc380900 ("ipc: Free mq_sysctls if ipc namespace creation
failed")
Here's a similar memory leak to the one fixed by the patch above.
retire_mq_sysctls need to be called when init_mqueue_fs fails after
setup_mq_sysctls.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg-5.15
linux-lowlatency
S
Wiz
CVE-2026-23104 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23104 [MEDIUM] CVE-2026-23104 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23104 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: fix devlink reload call trace
Commit 4da71a77fc3b ("ice: read internal temperature sensor") introduced
internal temperature sensor reading via HWMON. ice_hwmon_init() was added
to ice_init_feature() and ice_hwmon_exit() was added to ice_remove(). As a
result if devlink reload is used to reinit the device and then the driver
is removed, a call trace can occur.
BUG: unable to handle page fault for address: ffffffffc0fd4b5d
Call Trace:
string+0x48/0xe0
vsnprintf+0x1f9/0x650
sprintf+0x62/0x80
name_show+0x1f/0x30
dev_attr_show+0x19/0x60
The call trace repeats approximately every 10 minutes when system
monitoring tools (e.g., sadc) attempt to read
Wiz
CVE-2026-22979 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22979 [MEDIUM] CVE-2026-22979 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22979 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: fix memory leak in skb_segment_list for GRO packets
When skb_segment_list() is called during packet forwarding, it handles
packets that were aggregated by the GRO engine.
Historically, the segmentation logic in skb_segment_list assumes that
individual segments are split from a parent SKB and may need to carry
their own socket memory accounting. Accordingly, the code transfers
truesize from the parent to the newly created segments.
Prior to commit ed4cccef64c1 ("gro: fix ownership transfer"), this
truesize subtraction in skb_segment_list() was valid because fragments
still carry a reference to the original socket.
However, commit ed4cccef64c1
Wiz
CVE-2026-23260 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23260 CVE-2026-23260 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23260 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regmap: maple: free entry on mas_store_gfp() failure
regcache_maple_write() allocates a new block ('entry') to merge
adjacent ranges and then stores it with mas_store_gfp().
When mas_store_gfp() fails, the new 'entry' remains allocated and
is never freed, leaking memory.
Free 'entry' on the failure path; on success continue freeing the
replaced neighbor blocks ('lower', 'upper').
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probabi
Wiz
CVE-2026-23455 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23455 CVE-2026-23455 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23455 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_h323: check for zero length in DecodeQ931()
In DecodeQ931(), the UserUserIE code path reads a 16-bit length from
the packet, then decrements it by 1 to skip the protocol discriminator
byte before passing it to DecodeH323_UserInformation(). If the encoded
length is 0, the decrement wraps to -1, which is then passed as a
large value to the decoder, leading to an out-of-bounds read.
Add a check to ensure len is positive after the decrement.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV
Wiz
CVE-2025-71200 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71200 [MEDIUM] CVE-2025-71200 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71200 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: sdhci-of-dwcmshc: Prevent illegal clock reduction in HS200/HS400 mode
When operating in HS200 or HS400 timing modes, reducing the clock frequency
below 52MHz will lead to link broken as the Rockchip DWC MSHC controller
requires maintaining a minimum clock of 52MHz in these modes.
Add a check to prevent illegal clock reduction through debugfs:
root@debian:/# echo 50000000 > /sys/kernel/debug/mmc0/clock
root@debian:/# [ 30.090146] mmc0: running CQE recovery
mmc0: cqhci: Failed to halt
mmc0: cqhci: spurious TCN for tag 0
WARNING: drivers/mmc/host/cqhci-core.c:797 at cqhci_irq+0x254/0x818, CPU#1: kworker/1:0H/24
Modules linked in:
CPU: 1 UID: 0 P
Wiz
CVE-2022-50752 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50752 CVE-2022-50752 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50752 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid5: Remove unnecessary bio_put() in raid5_read_one_chunk()
When running chunk-sized reads on disks with badblocks duplicate bio
free/puts are observed:
## =============================================================================
BUG bio-200 (Not tainted): Object already free
Allocated in mempool_alloc_slab+0x17/0x20 age=3 cpu=2 pid=7504
__slab_alloc.constprop.0+0x5a/0xb0
kmem_cache_alloc+0x31e/0x330
mempool_alloc_slab+0x17/0x20
mempool_alloc+0x100/0x2b0
bio_alloc_bioset+0x181/0x460
do_mpage_readpage+0x776/0xd00
mpage_readahead+0x166/0x320
blkdev_readahead+0x15/0x20
read_pages+0x13f/0x5f0
page_cache_ra_unbounded+0x18d/0x220
force_page_c
Wiz
CVE-2023-53827 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53827 CVE-2023-53827 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53827 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: L2CAP: Fix use-after-free in l2cap_disconnect_{req,rsp}
Similar to commit d0be8347c623 ("Bluetooth: L2CAP: Fix use-after-free
caused by l2cap_chan_put"), just use l2cap_chan_hold_unless_zero to
prevent referencing a channel that is about to be destroyed.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules
kernel-rt-64k-debug
Sources
NVD
Debian 1
Wiz
CVE-2025-71231 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71231 [HIGH] CVE-2025-71231 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71231 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: iaa - Fix out-of-bounds index in find_empty_iaa_compression_mode
The local variable 'i' is initialized with -EINVAL, but the for loop
immediately overwrites it and -EINVAL is never returned.
If no empty compression mode can be found, the function would return the
out-of-bounds index IAA_COMP_MODES_MAX, which would cause an invalid
array access in add_iaa_compression_mode().
Fix both issues by returning either a valid index or -EINVAL.
Source : NVD
## 7.1
Score
Published February 18, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release D
Wiz
CVE-2025-71188 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71188 [MEDIUM] CVE-2025-71188 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71188 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: lpc18xx-dmamux: fix device leak on route allocation
Make sure to drop the reference taken when looking up the DMA mux
platform device during route allocation.
Note that holding a reference to a device does not prevent its driver
data from going away so there is no point in keeping the reference.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.5
Exploitation Probability (EPSS) N/A
Affected packages and
Wiz
CVE-2022-50768 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50768 CVE-2022-50768 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50768 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: smartpqi: Correct device removal for multi-actuator devices
Correct device count for multi-actuator drives which can cause kernel
panics.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug-devel-matched
linux-gcp
Sources
NVD
Debian 11 No Fix Added at: Dec 26, 2025
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Wiz
CVE-2025-68773 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68773 CVE-2025-68773 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68773 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: fsl-cpm: Check length parity before switching to 16 bit mode
Commit fc96ec826bce ("spi: fsl-cpm: Use 16 bit mode for large transfers
with even size") failed to make sure that the size is really even
before switching to 16 bit mode. Until recently the problem went
unnoticed because kernfs uses a pre-allocated bounce buffer of size
PAGE_SIZE for reading EEPROM.
But commit 8ad6249c51d0 ("eeprom: at25: convert to spi-mem API")
introduced an additional dynamically allocated bounce buffer whose size
is exactly the size of the transfer, leading to a buffer overrun in
the fsl-cpm driver when that size is odd.
Add the missing length parity verificatio
Wiz
CVE-2025-68794 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68794 CVE-2025-68794 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68794 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iomap: adjust read range correctly for non-block-aligned positions
iomap_adjust_read_range() assumes that the position and length passed in
are block-aligned. This is not always the case however, as shown in the
syzbot generated case for erofs. This causes too many bytes to be
skipped for uptodate blocks, which results in returning the incorrect
position and length to read in. If all the blocks are uptodate, this
underflows length and returns a position beyond the folio.
Fix the calculation to also take into account the block offset when
calculating how many bytes can be skipped for uptodate blocks.
Source : NVD
Published January 13, 2026
CNA Sc
Wiz
CVE-2026-31400 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31400 CVE-2026-31400 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31400 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sunrpc: fix cache_request leak in cache_release
When a reader's file descriptor is closed while in the middle of reading
a cache_request (rp->offset != 0), cache_release() decrements the
request's readers count but never checks whether it should free the
request.
In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the
cache_request is removed from the queue and freed along with its buffer
and cache_head reference. cache_release() lacks this cleanup.
The only other path that frees requests with readers == 0 is
cache_dequeue(), but it runs only when CACHE_PENDING transitions from
set to clear. If that transition already happened whi
Wiz
CVE-2025-40336 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40336 CVE-2025-40336 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40336 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/gpusvm: fix hmm_pfn_to_map_order() usage
Handle the case where the hmm range partially covers a huge page (like
2M), otherwise we can potentially end up doing something nasty like
mapping memory which is outside the range, and maybe not even mapped by
the mm. Fix is based on the xe userptr code, which in a future patch
will directly use gpusvm, so needs alignment here.
v2:
Add kernel-doc (Matt B)
s/fls/ilog2/ (Thomas)
Source : NVD
## 6.4
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV D
Wiz
CVE-2025-68226 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68226 CVE-2025-68226 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68226 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix incomplete backport in cfids_invalidation_worker()
The previous commit bdb596ceb4b7 ("smb: client: fix potential UAF in
smb2_close_cached_fid()") was an incomplete backport and missed one
kref_put() call in cfids_invalidation_worker() that should have been
converted to close_cached_dir().
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel6.12-tools-debugin
Wiz
CVE-2026-22976 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22976 [MEDIUM] CVE-2026-22976 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22976 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: sch_qfq: Fix NULL deref when deactivating inactive aggregate in qfq_reset
qfq_class->leaf_qdisc->q.qlen > 0
Two qfq_class objects may point to the same leaf_qdisc. This happens
when:
one QFQ qdisc is attached to the dev as the root qdisc, and
another QFQ qdisc is temporarily referenced (e.g., via qdisc_get()
/ qdisc_put()) and is pending to be destroyed, as in function
tc_new_tfilter.
When packets are enqueued through the root QFQ qdisc, the shared
leaf_qdisc->q.qlen increases. At the same time, the second QFQ
qdisc triggers qdisc_put and qdisc_destroy: the qdisc enters
qfq_reset() with its own q->q.qlen == 0, but its class's leaf
qd
Wiz
CVE-2026-23020 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23020 [MEDIUM] CVE-2026-23020 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23020 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: 3com: 3c59x: fix possible null dereference in vortex_probe1()
pdev can be null and free_ring: can be called in 1297 with a null
pdev.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-devel
linux-azure-4.15
Sources
NVD
CBL-Mariner 3.0 Severity MEDIUM Has Fix Added at: Feb 12, 2026
Debian 11, 12, 13, 14 Severity MEDIUM Has Fix
Wiz
CVE-2026-23157 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23157 [MEDIUM] CVE-2026-23157 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23157 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: do not strictly require dirty metadata threshold for metadata writepages
[BUG]
There is an internal report that over 1000 processes are
waiting at the io_schedule_timeout() of balance_dirty_pages(), causing
a system hang and trigger a kernel coredump.
The kernel is v6.4 kernel based, but the root problem still applies to
any upstream kernel before v6.18.
[CAUSE]
From Jan Kara for his wisdom on the dirty page balance behavior first.
This cgroup dirty limit was what was actually playing the role here
because the cgroup had only a small amount of memory and so the dirty
limit for it was something like 16MB.
Dirty throttling is responsible fo
Wiz
CVE-2023-54166 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54166 CVE-2023-54166 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54166 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
igc: Fix Kernel Panic during ndo_tx_timeout callback
The Xeon validation group has been carrying out some loaded tests
with various HW configurations, and they have seen some transmit
queue time out happening during the test. This will cause the
reset adapter function to be called by igc_tx_timeout().
Similar race conditions may arise when the interface is being brought
down and up in igc_reinit_locked(), an interrupt being generated, and
igc_clean_tx_irq() being called to complete the TX.
When the igc_tx_timeout() function is invoked, this patch will turn
off all TX ring HW queues during igc_down() process. TX ring HW queues
will be activated agai
Wiz
CVE-2026-23229 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23229 [MEDIUM] CVE-2026-23229 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23229 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: virtio - Add spinlock protection with virtqueue notification
When VM boots with one virtio-crypto PCI device and builtin backend,
run openssl benchmark command with multiple processes, such as
openssl speed -evp aes-128-cbc -engine afalg -seconds 10 -multi 32
openssl processes will hangup and there is error reported like this:
virtio_crypto virtio0: dataq.0:id 3 is not a head!
It seems that the data virtqueue need protection when it is handled
for virtio done notification. If the spinlock protection is added
in virtcrypto_done_task(), openssl benchmark with multiple processes
works well.
Source : NVD
## 5.5
Score
Published February 1
Wiz
CVE-2023-53862 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53862 CVE-2023-53862 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53862 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfs: fix missing hfs_bnode_get() in __hfs_bnode_create
Syzbot found a kernel BUG in hfs_bnode_put():
kernel BUG at fs/hfs/bnode.c:466!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 3634 Comm: kworker/u4:5 Not tainted 6.1.0-rc7-syzkaller-00190-g97ee9d1c1696 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
Workqueue: writeback wb_workfn (flush-7:0)
RIP: 0010:hfs_bnode_put+0x46f/0x480 fs/hfs/bnode.c:466
Code: 8a 80 ff e9 73 fe ff ff 89 d9 80 e1 07 80 c1 03 38 c1 0f 8c a0 fe ff ff 48 89 df e8 db 8a 80 ff e9 93 fe ff ff e8 a1 68 2c ff 0b e8 9a 68 2c ff 0f 0b 0f 1f 84 00 00 00 00 00 55 41 57 41 56
RSP
Wiz
CVE-2023-54093 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54093 CVE-2023-54093 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54093 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: anysee: fix null-ptr-deref in anysee_master_xfer
In anysee_master_xfer, msg is controlled by user. When msg[i].buf
is null and msg[i].len is zero, former checks on msg[i].buf would be
passed. Malicious data finally reach anysee_master_xfer. If accessing
msg[i].buf[0] without sanity check, null ptr deref would happen.
We add check on msg[i].len to prevent crash.
Similar commit:
commit 0ed554fd769a
("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")
[hverkuil: add spaces around +]
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Ex
Wiz
CVE-2025-71203 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.0
CVE-2025-71203 [HIGH] CVE-2025-71203 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71203 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
riscv: Sanitize syscall table indexing under speculation
The syscall number is a user-controlled value used to index into the
syscall table. Use array_index_nospec() to clamp this value after the
bounds check to prevent speculative out-of-bounds access and subsequent
data leakage via cache side channels.
Source : NVD
## 7
Score
Published February 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.3
Exploitation Probability (EPSS) N/A
Affected packages and librar
Wiz
CVE-2023-54284 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54284 CVE-2023-54284 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54284 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: av7110: prevent underflow in write_ts_to_decoder()
The buf[4] value comes from the user via ts_play(). It is a value in
the u8 range. The final length we pass to av7110_ipack_instant_repack()
is "len - (buf[4] + 1) - 4" so add a check to ensure that the length is
not negative. It's not clear that passing a negative len value does
anything bad necessarily, but it's not best practice.
With the new bounds checking the "if (!len)" condition is no longer
possible or required so remove that.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
Wiz
CVE-2025-68230 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68230 CVE-2025-68230 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68230 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: fix gpu page fault after hibernation on PF passthrough
On PF passthrough environment, after hibernate and then resume, coralgemm
will cause gpu page fault.
Mode1 reset happens during hibernate, but partition mode is not restored
on resume, register mmCP_HYP_XCP_CTL and mmCP_PSP_XCP_CTL is not right
after resume. When CP access the MQD BO, wrong stride size is used,
this will cause out of bound access on the MQD BO, resulting page fault.
The fix is to ensure gfx_v9_4_3_switch_compute_partition() is called
when resume from a hibernation.
KFD resume is called separately during a reset recovery or resume from
suspend sequence. Hence it's n
Wiz
CVE-2023-54272 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54272 CVE-2023-54272 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54272 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix a possible null-pointer dereference in ni_clear()
In a previous commit c1006bd13146, ni->mi.mrec in ni_write_inode()
could be NULL, and thus a NULL check is added for this variable.
However, in the same call stack, ni->mi.mrec can be also dereferenced
in ni_clear():
ntfs_evict_inode(inode)
ni_write_inode(inode, ...)
ni = ntfs_i(inode);
is_rec_inuse(ni->mi.mrec) -> Add a NULL check by previous commit
ni_clear(ntfs_i(inode))
is_rec_inuse(ni->mi.mrec) -> No check
Thus, a possible null-pointer dereference may exist in ni_clear().
To fix it, a NULL check is added in this function.
Source : NVD
Published December 30, 2025
CNA Score N/A
Wiz
CVE-2023-54046 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54046 CVE-2023-54046 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54046 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: essiv - Handle EBUSY correctly
As it is essiv only handles the special return value of EINPROGERSS,
which means that in all other cases it will free data related to the
request.
However, as the caller of essiv may specify MAY_BACKLOG, we also need
to expect EBUSY and treat it in the same way. Otherwise backlogged
requests will trigger a use-after-free.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Wiz
CVE-2022-50871 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50871 CVE-2022-50871 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50871 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: Fix qmi_msg_handler data structure initialization
qmi_msg_handler is required to be null terminated by QMI module.
There might be a case where a handler for a msg id is not present in the
handlers array which can lead to infinite loop while searching the handler
and therefore out of bound access in qmi_invoke_handler().
Hence update the initialization in qmi_msg_handler data structure.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N
Wiz
CVE-2026-23329 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23329 CVE-2026-23329 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23329 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libie: don't unroll if fwlog isn't supported
The libie_fwlog_deinit() function can be called during driver unload
even when firmware logging was never properly initialized. This led to call
trace:
[ 148.576156] Oops: Oops: 0000 [#1] SMP NOPTI
[ 148.576167] CPU: 80 UID: 0 PID: 12843 Comm: rmmod Kdump: loaded Not tainted 6.17.0-rc7next-queue-3oct-01915-g06d79d51cf51 #1 PREEMPT(full)
[ 148.576177] Hardware name: HPE ProLiant DL385 Gen10 Plus/ProLiant DL385 Gen10 Plus, BIOS A42 07/18/2020
[ 148.576182] RIP: 0010:__dev_printk+0x16/0x70
[ 148.576196] Code: 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 55 41 54 49 89 d4 55
Wiz
CVE-2023-53996 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53996 CVE-2023-53996 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53996 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/sev: Make enc_dec_hypercall() accept a size instead of npages
enc_dec_hypercall() accepted a page count instead of a size, which
forced its callers to round up. As a result, non-page aligned
vaddrs caused pages to be spuriously marked as decrypted via the
encryption status hypercall, which in turn caused consistent
corruption of pages during live migration. Live migration requires
accurate encryption status information to avoid migrating pages
from the wrong perspective.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date
Wiz
CVE-2023-54153 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54153 CVE-2023-54153 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54153 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: turn quotas off if mount failed after enabling quotas
Yi found during a review of the patch "ext4: don't BUG on inconsistent
journal feature" that when ext4_mark_recovery_complete() returns an error
value, the error handling path does not turn off the enabled quotas,
which triggers the following kmemleak:
unreferenced object 0xffff8cf68678e7c0 (size 64):
comm "mount", pid 746, jiffies 4294871231 (age 11.540s)
hex dump (first 32 bytes):
00 90 ef 82 f6 8c ff ff 00 00 00 00 41 01 00 00 ............A...
c7 00 00 00 bd 00 00 00 0a 00 00 00 48 00 00 00 ............H...
backtrace:
[] __kmem_cache_alloc_node+0x4d4/0x880
[] kmalloc_trace+0x39/0x140
[]
Wiz
CVE-2026-23368 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23368 CVE-2026-23368 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23368 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: phy: register phy led_triggers during probe to avoid AB-BA deadlock
There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and
LED_TRIGGER_PHY are enabled:
[ 1362.049207] [] led_trigger_register+0x5c/0x1fc ] phy_led_triggers_register+0xd0/0x234
[ 1362.060329] [] phy_attach_direct+0x33c/0x40c
[ 1362.065489] [] phylink_fwnode_phy_connect+0x15c/0x23c
[ 1362.071480] [] mtk_open+0x7c/0xba0
[ 1362.075849] [] __dev_open+0x280/0x2b0
[ 1362.080384] [] __dev_change_flags+0x244/0x24c
[ 1362.085598] [] dev_change_flags+0x28/0x78
[ 1362.090528] [] dev_ioctl+0x4c0/0x654 ] sock_ioctl+0x2f4/0x4e0
[ 1362.099567] [] sys_ioctl+0x32c/0xd8c
[ 1362.104022] [] sys
Wiz
CVE-2025-71144 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71144 [MEDIUM] CVE-2025-71144 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71144 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: ensure context reset on disconnect()
send_fastclose flag
request_mptcp
WARNING: CPU: 26 PID: 8996 at net/mptcp/subflow.c:1519 subflow_data_ready (net/mptcp/subflow.c:1519 (discriminator 13))
Modules linked in:
CPU: 26 UID: 0 PID: 8996 Comm: syz.22.39 Not tainted 6.18.0-rc7-05427-g11fc074f6c36 #1 PREEMPT(voluntary)
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
RIP: 0010:subflow_data_ready (net/mptcp/subflow.c:1519 (discriminator 13))
Code: 90 0f 0b 90 90 e9 04 fe ff ff e8 b7 1e f5 fe 89 ee bf 07 00 00 00 e8 db 19 f5 fe 83 fd 07 0f 84 35 ff ff ff e8 9d 1e f5 fe 90 0b 90 e9 27 ff ff ff e8 8f 1e f5 fe 4c 89 e7 48 89 de e8 14 09
RSP: 0018:ff
Wiz
CVE-2025-71148 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 3.3
CVE-2025-71148 [LOW] CVE-2025-71148 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71148 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/handshake: restore destructor on submit failure
handshake_req_submit() replaces sk->sk_destruct but never restores it when
submission fails before the request is hashed. handshake_sk_destruct() then
returns early and the original destructor never runs, leaking the socket.
Restore sk_destruct on the error path.
Source : NVD
## 3.3
Score
Published January 23, 2026
Severity LOW
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages a
Wiz
CVE-2023-54308 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54308 CVE-2023-54308 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54308 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: ymfpci: Create card with device-managed snd_devm_card_new()
snd_card_ymfpci_remove() was removed in commit c6e6bb5eab74 ("ALSA:
ymfpci: Allocate resources with device-managed APIs"), but the call to
snd_card_new() was not replaced with snd_devm_card_new().
Since there was no longer a call to snd_card_free, unloading the module
would eventually result in Oops:
[697561.532887] BUG: unable to handle page fault for address: ffffffffc0924480
[697561.532893] #PF: supervisor read access in kernel mode
[697561.532896] #PF: error_code(0x0000) - not-present page
[697561.532899] PGD ae1e15067 P4D ae1e15067 PUD ae1e17067 PMD 11a8f5067 PTE 0
[697561.5329
Wiz
CVE-2023-54076 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54076 CVE-2023-54076 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54076 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix missed ses refcounting
Use new cifs_smb_ses_inc_refcount() helper to get an active reference
of @ses and @ses->dfs_root_ses (if set). This will prevent
@ses->dfs_root_ses of being put in the next call to cifs_put_smb_ses()
and thus potentially causing an use-after-free bug.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-source-vanilla
kernel-azure-dev
Wiz
CVE-2022-50781 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50781 CVE-2022-50781 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50781 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
amdgpu/pm: prevent array underflow in vega20_odn_edit_dpm_table()
In the PP_OD_EDIT_VDDC_CURVE case the "input_index" variable is capped at
2 but not checked for negative values so it results in an out of bounds
read. This value comes from the user via sysfs.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-5.15
linux-gcp-5.4
Sources
NVD
Debian 11, 12, 13, 14 Has
Wiz
CVE-2026-23165 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23165 [MEDIUM] CVE-2026-23165 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23165 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sfc: fix deadlock in RSS config read
Since cited commit, core locks the net_device's rss_lock when handling
ethtool -x command, so driver's implementation should not lock it
again. Remove the latter.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-core
kernel-devel-matched
Sources
NVD
Debian 14 Severity MEDIUM Has Fix Ad
Wiz
CVE-2025-71232 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71232 [MEDIUM] CVE-2025-71232 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71232 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Free sp in error path to fix system crash
System crash seen during load/unload test in a loop,
[61110.449331] qla2xxx [0000:27:00.0]-0042:0: Disabled MSI-X.
[61110.467494] =============================================================================
[61110.467498] BUG qla2xxx_srbs (Tainted: G OE -------- --- ): Objects remaining in qla2xxx_srbs on __kmem_cache_shutdown()
[61110.467501] -----------------------------------------------------------------------------
[61110.467502] Slab 0x000000000ffc8162 objects=51 used=1 fp=0x00000000e25d3d85 flags=0x57ffffc0010200(slab|head|node=1|zone=2|lastcpupid=0x1fffff)
[61110.467509] CPU: 53 PID
Wiz
CVE-2022-50867 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50867 CVE-2022-50867 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50867 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/a6xx: Fix kvzalloc vs state_kcalloc usage
adreno_show_object() is a trap! It will re-allocate the pointer it is
passed on first call, when the data is ascii85 encoded, using kvmalloc/
kvfree(). Which means the data passed to it must be kvmalloc'd, ie.
we cannot use the state_kcalloc() helper.
This partially reverts commit ec8f1813bf8d ("drm/msm/a6xx: Replace
kcalloc() with kvzalloc()"), but adds the missing kvfree() to fix the
memory leak that was present previously. And adds a warning comment.
Patchwork: https://patchwork.freedesktop.org/patch/507014/
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux
Wiz
CVE-2026-23463 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23463 CVE-2026-23463 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23463 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
soc: fsl: qbman: fix race condition in qman_destroy_fq
When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between
fq_table[fq->idx] state and freeing/allocating from the pool and
WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered.
Indeed, we can have:
Thread A Thread B
qman_destroy_fq() qman_create_fq()
qman_release_fqid()
qman_shutdown_fq()
gen_pool_free()
-- At this point, the fqid is available again --
qman_alloc_fqid()
-- so, we can get the just-freed fqid in thread B --
fq->fqid = fqid;
fq->idx = fqid * 2;
WARN_ON(fq_table[fq->idx]);
fq_table[fq->idx] = fq;
fq_table[fq->idx] = NULL;
And adding some logs between qman_re
Wiz
CVE-2025-71239 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71239 CVE-2025-71239 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71239 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
audit: add fchmodat2() to change attributes class
fchmodat2(), introduced in version 6.6 is currently not in the change
attribute class of audit. Calling fchmodat2() to change a file
attribute in the same fashion than chmod() or fchmodat() will bypass
audit rules such as:
-w /tmp/test -p rwa -k test_rwa
The current patch adds fchmodat2() to the change attributes class.
Source : NVD
## 5.1
Score
Published March 17, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.
Wiz
CVE-2023-54319 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54319 CVE-2023-54319 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54319 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pinctrl: at91-pio4: check return value of devm_kasprintf()
devm_kasprintf() returns a pointer to dynamically allocated memory.
Pointer could be NULL in case allocation fails. Check pointer validity.
Identified with coccinelle (kmerr.cocci script).
Depends-on: 1c4e5c470a56 ("pinctrl: at91: use devm_kasprintf() to avoid potential leaks")
Depends-on: 5a8f9cf269e8 ("pinctrl: at91-pio4: use proper format specifier for unsigned int")
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Pro
Wiz
CVE-2025-68749 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2025-68749 [MEDIUM] CVE-2025-68749 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68749 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
accel/ivpu: Fix race condition when unbinding BOs
Fix 'Memory manager not clean during takedown' warning that occurs
when ivpu_gem_bo_free() removes the BO from the BOs list before it
gets unmapped. Then file_priv_unbind() triggers a warning in
drm_mm_takedown() during context teardown.
Protect the unmapping sequence with bo_list_lock to ensure the BO is
always fully unmapped when removed from the list. This ensures the BO
is either fully unmapped at context teardown time or present on the
list and unmapped by file_priv_unbind().
Source : NVD
## 4.7
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linu
Wiz
CVE-2026-23354 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23354 CVE-2026-23354 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23354 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/fred: Correct speculative safety in fred_extint()
array_index_nospec() is no use if the result gets spilled to the stack, as
it makes the believed safe-under-speculation value subject to memory
predictions.
For all practical purposes, this means array_index_nospec() must be used in
the expression that accesses the array.
As the code currently stands, it's the wrong side of irqentry_enter(), and
'index' is put into %ebp across the function call.
Remove the index variable and reposition array_index_nospec(), so it's
calculated immediately before the array access.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Lin
Wiz
CVE-2026-22987 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22987 [MEDIUM] CVE-2026-22987 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22987 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: act_api: avoid dereferencing ERR_PTR in tcf_idrinfo_destroy
syzbot reported a crash in tc_act_in_hw() during netns teardown where
tcf_idrinfo_destroy() passed an ERR_PTR(-EBUSY) value as a tc_action
pointer, leading to an invalid dereference.
Guard against ERR_PTR entries when iterating the action IDR so teardown
does not call tc_act_in_hw() on an error pointer.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EP
Wiz
CVE-2026-23199 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23199 [MEDIUM] CVE-2026-23199 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23199 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
procfs: avoid fetching build ID while holding VMA lock
Fix PROCMAP_QUERY to fetch optional build ID only after dropping mmap_lock
or per-VMA lock, whichever was used to lock VMA under question, to avoid
deadlock reported by syzbot:
-> #1 (&mm->mmap_lock){++++}-{4:4}:
__might_fault+0xed/0x170
_copy_to_iter+0x118/0x1720
copy_page_to_iter+0x12d/0x1e0
filemap_read+0x720/0x10a0
blkdev_read_iter+0x2b5/0x4e0
vfs_read+0x7f4/0xae0
ksys_read+0x12a/0x250
do_syscall_64+0xcb/0xf80
entry_SYSCALL_64_after_hwframe+0x77/0x7f
-> #0 (&sb->s_type->i_mutex_key#8){++++}-{4:4}:
__lock_acquire+0x1509/0x26d0
lock_acquire+0x185/0x340
down_read+0x98/0x490
blkdev_read_iter+0
Wiz
CVE-2026-23152 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23152 [MEDIUM] CVE-2026-23152 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23152 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: correctly decode TTLM with default link map
TID-To-Link Mapping (TTLM) elements do not contain any link mapping
presence indicator if a default mapping is used and parsing needs to be
skipped.
Note that access points should not explicitly report an advertised TTLM
with a default mapping as that is the implied mapping if the element is
not included, this is even the case when switching back to the default
mapping. However, mac80211 would incorrectly parse the frame and would
also read one byte beyond the end of the element.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technolog
Wiz
CVE-2026-23171 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23171 [HIGH] CVE-2026-23171 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23171 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bonding: fix use-after-free due to enslave fail after slave array update
Fix a use-after-free which happens due to enslave failure after the new
slave has been added to the array. Since the new slave can be used for Tx
immediately, we can use it after it has been freed by the enslave error
cleanup path which frees the allocated slave memory. Slave update array is
supposed to be called last when further enslave failures are not expected.
Move it after xdp setup to avoid any problems.
It is very easy to reproduce the problem with a simple xdp_pass prog:
ip l add bond1 type bond mode balance-xor
ip l set bond1 up
ip l set dev bond1 xdp object xdp_pass
Wiz
CVE-2025-71122 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71122 [HIGH] CVE-2025-71122 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71122 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommufd/selftest: Check for overflow in IOMMU_TEST_OP_ADD_RESERVED
syzkaller found it could overflow math in the test infrastructure and
cause a WARN_ON by corrupting the reserved interval tree. This only
effects test kernels with CONFIG_IOMMUFD_TEST.
Validate the user input length in the test ioctl.
Source : NVD
## 7.8
Score
Published January 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.5
Exploitation Probability (EPSS) N/A
Affected packages and librarie
Wiz
CVE-2026-23306 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23306 [HIGH] CVE-2026-23306 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23306 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: pm8001: Fix use-after-free in pm8001_queue_command()
Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors
pm8001_queue_command(), however it introduces a potential cause of a double
free scenario when it changes the function to return -ENODEV in case of phy
down/device gone state.
In this path, pm8001_queue_command() updates task status and calls
task_done to indicate to upper layer that the task has been handled.
However, this also frees the underlying SAS task. A -ENODEV is then
returned to the caller. When libsas sas_ata_qc_issue() receives this error
value, it assumes the task wasn't handled/queued by LLDD and proce
Wiz
CVE-2026-23389 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23389 CVE-2026-23389 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23389 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: Fix memory leak in ice_set_ringparam()
In ice_set_ringparam, tx_rings and xdp_rings are allocated before
rx_rings. If the allocation of rx_rings fails, the code jumps to
the done label leaking both tx_rings and xdp_rings. Furthermore, if
the setup of an individual Rx ring fails during the loop, the code jumps
to the free_tx label which releases tx_rings but leaks xdp_rings.
Fix this by introducing a free_xdp label and updating the error paths to
ensure both xdp_rings and tx_rings are properly freed if rx_rings
allocation or setup fails.
Compile tested only. Issue found using a prototype static analysis tool
and code review.
Source : NVD
##
Wiz
CVE-2023-54277 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54277 CVE-2023-54277 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54277 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fbdev: udlfb: Fix endpoint check
The syzbot fuzzer detected a problem in the udlfb driver, caused by an
endpoint not having the expected type:
usb 1-1: Read EDID byte 0 failed: -71
usb 1-1: Unable to get valid EDID from device/display
------------[ cut here ]------------
usb 1-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 0 PID: 9 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880
drivers/usb/core/urb.c:504
Modules linked in:
CPU: 0 PID: 9 Comm: kworker/0:1 Not tainted
6.4.0-rc1-syzkaller-00016-ga4422ff22142 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
04/28/2023
Workqueue: usb_hub_wq hub_event
RIP: 0
Wiz
CVE-2022-50868 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50868 CVE-2022-50868 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50868 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hwrng: amd - Fix PCI device refcount leak
for_each_pci_dev() is implemented by pci_get_device(). The comment of
pci_get_device() says that it will increase the reference count for the
returned pci_dev and also decrease the reference count for the input
pci_dev @from if it is not NULL.
If we break for_each_pci_dev() loop with pdev not NULL, we need to call
pci_dev_put() to decrease the reference count. Add the missing
pci_dev_put() for the normal and error path.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2025-68182 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68182 CVE-2025-68182 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68182 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: iwlwifi: fix potential use after free in iwl_mld_remove_link()
This code frees "link" by calling kfree_rcu(link, rcu_head) and then it
dereferences "link" to get the "link->fw_id". Save the "link->fw_id"
first to avoid a potential use after free.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-internal
kernel-debug-core
Sources
NVD
Debian 14 Has Fi
Wiz
CVE-2026-22998 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-22998 [HIGH] CVE-2026-22998 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22998 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-tcp: fix NULL pointer dereferences in nvmet_tcp_build_pdu_iovec
Commit efa56305908b ("nvmet-tcp: Fix a kernel panic when host sends an invalid H2C PDU length")
added ttag bounds checking and data_offset
validation in nvmet_tcp_handle_h2c_data_pdu(), but it did not validate
whether the command's data structures (cmd->req.sg and cmd->iov) have
been properly initialized before processing H2C_DATA PDUs.
The nvmet_tcp_build_pdu_iovec() function dereferences these pointers
without NULL checks. This can be triggered by sending H2C_DATA PDU
immediately after the ICREQ/ICRESP handshake, before
sending a CONNECT command or NVMe write command.
Attack ve
Wiz
CVE-2026-23008 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23008 [MEDIUM] CVE-2026-23008 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23008 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/vmwgfx: Fix KMS with 3D on HW version 10
HW version 10 does not have GB Surfaces so there is no backing buffer for
surface backed FBs. This would result in a nullptr dereference and crash
the driver causing a black screen.
Source : NVD
## 5.5
Score
Published January 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-devel
kernel-rt-modules
Sources
NVD
Debian 14 Severity ME
Wiz
CVE-2023-53832 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53832 CVE-2023-53832 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53832 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid10: fix null-ptr-deref in raid10_sync_request
init_resync() inits mempool and sets conf->have_replacemnt at the beginning
of sync, close_sync() frees the mempool when sync is completed.
After [1] recovery might be skipped and init_resync() is called but
close_sync() is not. null-ptr-deref occurs with r10bio->dev[i].repl_bio.
The following is one way to reproduce the issue.
create a array, wait for resync to complete, mddev->recovery_cp is set
to MaxSector.
recovery is woken and it is skipped. conf->have_replacement is set to 0 in init_resync(). close_sync() not called.
some io errors and rdev A is set to WantReplacement.
a new device is
Wiz
CVE-2023-54035 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54035 CVE-2023-54035 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54035 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: fix underflow in chain reference counter
Set element addition error path decrements reference counter on chains
twice: once on element release and again via nft_data_release().
Then, d6b478666ffa ("netfilter: nf_tables: fix underflow in object
reference counter") incorrectly fixed this by removing the stateful
object reference count decrement.
Restore the stateful object decrement as in b91d90368837 ("netfilter:
nf_tables: fix leaking object reference count") and let
nft_data_release() decrement the chain reference counter, so this is
done only once.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technolo
Wiz
CVE-2022-50760 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50760 CVE-2022-50760 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50760 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: Fix PCI device refcount leak in amdgpu_atrm_get_bios()
As comment of pci_get_class() says, it returns a pci_device with its
refcount increased and decreased the refcount for the input parameter
@from if it is not NULL.
If we break the loop in amdgpu_atrm_get_bios() with 'pdev' not NULL, we
need to call pci_dev_put() to decrease the refcount. Add the missing
pci_dev_put() to avoid refcount leak.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (E
Wiz
CVE-2025-71183 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71183 [MEDIUM] CVE-2025-71183 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71183 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: always detect conflicting inodes when logging inode refs
After rename exchanging (either with the rename exchange operation or
regular renames in multiple non-atomic steps) two inodes and at least
one of them is a directory, we can end up with a log tree that contains
only of the inodes and after a power failure that can result in an attempt
to delete the other inode when it should not because it was not deleted
before the power failure. In some case that delete attempt fails when
the target inode is a directory that contains a subvolume inside it, since
the log replay code is not prepared to deal with directory entries that
point to root ite
Wiz
CVE-2025-71145 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71145 [HIGH] CVE-2025-71145 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71145 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: phy: isp1301: fix non-OF device reference imbalance
A recent change fixing a device reference leak in a UDC driver
introduced a potential use-after-free in the non-OF case as the
isp1301_get_client() helper only increases the reference count for the
returned I2C device in the OF case.
Increment the reference count also for non-OF so that the caller can
decrement it unconditionally.
Note that this is inherently racy just as using the returned I2C device
is since nothing is preventing the PHY driver from being unbound while
in use.
Source : NVD
## 7.8
Score
Published January 23, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
L
Wiz
CVE-2023-54211 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54211 CVE-2023-54211 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54211 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Fix warning in trace_buffered_event_disable()
Warning happened in trace_buffered_event_disable() at
WARN_ON_ONCE(!trace_buffered_event_ref)
Call Trace:
? __warn+0xa5/0x1b0
? trace_buffered_event_disable+0x189/0x1b0
__ftrace_event_enable_disable+0x19e/0x3e0
free_probe_data+0x3b/0xa0
unregister_ftrace_function_probe_func+0x6b8/0x800
event_enable_func+0x2f0/0x3d0
ftrace_process_regex.isra.0+0x12d/0x1b0
ftrace_filter_write+0xe6/0x140
vfs_write+0x1c9/0x6f0
[...]
The cause of the warning is in __ftrace_event_enable_disable(),
trace_buffered_event_enable() was called once while
trace_buffered_event_disable() was called twice.
Reproduction script
Wiz
CVE-2023-54066 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54066 CVE-2023-54066 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54066 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: dvb-usb-v2: gl861: Fix null-ptr-deref in gl861_i2c_master_xfer
In gl861_i2c_master_xfer, msg is controlled by user. When msg[i].buf
is null and msg[i].len is zero, former checks on msg[i].buf would be
passed. Malicious data finally reach gl861_i2c_master_xfer. If accessing
msg[i].buf[0] without sanity check, null ptr deref would happen.
We add check on msg[i].len to prevent crash.
Similar commit:
commit 0ed554fd769a
("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CIS
Wiz
CVE-2023-54110 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54110 CVE-2023-54110 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54110 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: rndis_host: Secure rndis_query check against int overflow
Variables off and len typed as uint32 in rndis_query function
are controlled by incoming RNDIS response message thus their
value may be manipulated. Setting off to a unexpectetly large
value will cause the sum with len and 8 to overflow and pass
the implemented validation step. Consequently the response
pointer will be referring to a location past the expected
buffer boundaries allowing information leakage e.g. via
RNDIS_OID_802_3_PERMANENT_ADDRESS OID.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has
Wiz
CVE-2026-23296 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23296 CVE-2026-23296 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23296 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: core: Fix refcount leak for tagset_refcnt
This leak will cause a hang when tearing down the SCSI host. For example,
iscsid hangs with the following call trace:
[130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured
PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid"
#0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4
#1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f
#2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0
#3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f
#4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b
#5 [ffffb5b9c134bb30] iscsi_sw_tc
Wiz
CVE-2023-54312 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54312 CVE-2023-54312 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54312 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
samples/bpf: Fix buffer overflow in tcp_basertt
Using sizeof(nv) or strlen(nv)+1 is correct.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 13.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-nvidia
cluster-md-kmp-64kb
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW Has Fix Added at: Dec 31, 2025
Ubuntu 16.04 Severity MEDIUM No Fix Added
Wiz
CVE-2022-50736 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50736 CVE-2022-50736 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50736 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/siw: Fix immediate work request flush to completion queue
Correctly set send queue element opcode during immediate work request
flushing in post sendqueue operation, if the QP is in ERROR state.
An undefined ocode value results in out-of-bounds access to an array
for mapping the opcode between siw internal and RDMA core representation
in work completion generation. It resulted in a KASAN BUG report
of type 'global-out-of-bounds' during NFSoRDMA testing.
This patch further fixes a potential case of a malicious user which may
write undefined values for completion queue elements status or opcode,
if the CQ is memory mapped to user land. It avoids
Wiz
CVE-2025-71204 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71204 [MEDIUM] CVE-2025-71204 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71204 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb/server: fix refcount leak in parse_durable_handle_context()
When the command is a replay operation and -ENOEXEC is returned,
the refcount of ksmbd_file must be released.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-devel
kernel-debug-devel
Sources
NVD
Debian 11, 12 No Fix Added at: Feb 15, 2026
Debian 13, 14 Severity MEDIU
Wiz
CVE-2023-54014 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54014 CVE-2023-54014 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54014 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Check valid rport returned by fc_bsg_to_rport()
Klocwork reported warning of rport maybe NULL and will be dereferenced.
rport returned by call to fc_bsg_to_rport() could be NULL and dereferenced.
Check valid rport returned by fc_bsg_to_rport().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-abi-whitelists
kernel-ipaclones-internal
Sources
NVD
Debia
Wiz
CVE-2022-50755 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50755 CVE-2022-50755 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50755 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udf: Avoid double brelse() in udf_rename()
syzbot reported a warning like below [1]:
VFS: brelse: Trying to free free buffer
WARNING: CPU: 2 PID: 7301 at fs/buffer.c:1145 __brelse+0x67/0xa0
...
Call Trace: invalidate_bh_lru+0x99/0x150
smp_call_function_many_cond+0xe2a/0x10c0
? generic_remap_file_range_prep+0x50/0x50
? __brelse+0xa0/0xa0
? __mutex_lock+0x21c/0x12d0
? smp_call_on_cpu+0x250/0x250
? rcu_read_lock_sched_held+0xb/0x60
? lock_release+0x587/0x810
? __brelse+0xa0/0xa0
? generic_remap_file_range_prep+0x50/0x50
on_each_cpu_cond_mask+0x3c/0x80
blkdev_flush_mapping+0x13a/0x2f0
blkdev_put_whole+0xd3/0xf0
blkdev_put+0x222/0x760
deactivate_locked_
Wiz
CVE-2025-68771 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68771 CVE-2025-68771 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68771 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ocfs2: fix kernel BUG in ocfs2_find_victim_chain
cl_next_free_rec
To fix this, an if condition is introduced in ocfs2_claim_suballoc_bits(),
just before calling ocfs2_find_victim_chain(), the code block in it being
executed when either of the following conditions is true:
cl_next_free_rec
cl_next_free_rec
cl_count
Either of them being true is indicative of the fact that there are no
chains left for usage.
This is addressed using ocfs2_error(), which prints
the error log for debugging purposes, rather than panicking the kernel.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Publi
Wiz
CVE-2022-50746 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50746 CVE-2022-50746 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50746 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: validate the extent length for uncompressed pclusters
syzkaller reported a KASAN use-after-free: https://syzkaller.appspot.com/bug?extid=2ae90e873e97f1faf6f2
The referenced fuzzed image actually has two issues:
m_pa == 0 as a non-inlined pcluster;
The logical length is longer than its physical length.
The first issue has already been addressed. This patch addresses
the second issue by checking the extent length validity.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation P
Wiz
CVE-2025-68237 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68237 CVE-2025-68237 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68237 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mtdchar: fix integer overflow in read/write ioctls
The "req.start" and "req.len" variables are u64 values that come from the
user at the start of the function. We mask away the high 32 bits of
"req.len" so that's capped at U32_MAX but the "req.start" variable can go
up to U64_MAX which means that the addition can still integer overflow.
Use check_add_overflow() to fix this bug.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile
Wiz
CVE-2023-54261 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54261 CVE-2023-54261 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54261 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdkfd: Add missing gfx11 MQD manager callbacks
mqd_stride function was introduced in commit 2f77b9a242a2
("drm/amdkfd: Update MQD management on multi XCC setup")
but not assigned for gfx11. Fixes a NULL dereference in debugfs.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-default-extra
linux-aws-5.15
Sources
NVD
Debian 11, 12 No Fix Added at: Dec 31, 2025
De
Wiz
CVE-2025-71103 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71103 [MEDIUM] CVE-2025-71103 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71103 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm: adreno: fix deferencing ifpc_reglist when not declared
On plaforms with an a7xx GPU not supporting IFPC, the ifpc_reglist
if still deferenced in a7xx_patch_pwrup_reglist() which causes
a kernel crash:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
...
pc : a6xx_hw_init+0x155c/0x1e4c [msm]
lr : a6xx_hw_init+0x9a8/0x1e4c [msm]
...
Call trace:
a6xx_hw_init+0x155c/0x1e4c [msm] (P)
msm_gpu_hw_init+0x58/0x88 [msm]
adreno_load_gpu+0x94/0x1fc [msm]
msm_open+0xe4/0xf4 [msm]
drm_file_alloc+0x1a0/0x2e4 [drm]
drm_client_init+0x7c/0x104 [drm]
drm_fbdev_client_setup+0x94/0xcf0 [drm_client_lib]
drm_client_setup+0xb4/0
Wiz
CVE-2026-23293 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23293 CVE-2026-23293 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23293 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled
When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. If an IPv6 packet is injected into the interface,
route_shortcircuit() is called and a NULL pointer dereference happens on
neigh_lookup().
BUG: kernel NULL pointer dereference, address: 0000000000000380
Oops: Oops: 0000 [#1] SMP NOPTI
[...]
RIP: 0010:neigh_lookup+0x20/0x270
[...]
Call Trace: vxlan_xmit+0x638/0x1ef0 [vxlan]
dev_hard_start_xmit+0x9e/0x2e0
__dev_queue_xmit+0xbee/0x14e0
packet_sendmsg+0x116f/0x1930
__sys_sendto+0x1f5
Wiz
CVE-2023-54042 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54042 CVE-2023-54042 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54042 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/64s: Fix VAS mm use after free
The refcount on mm is dropped before the coprocessor is detached.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64kb
kernel-devel
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8, 9 Severity LOW No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04 Severity MEDIUM No Fi
Wiz
CVE-2025-68768 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68768 CVE-2025-68768 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68768 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
inet: frags: flush pending skbs in fqdir_pre_exit()
We have been seeing occasional deadlocks on pernet_ops_rwsem since
September in NIPA. The stuck task was usually modprobe (often loading
a driver like ipvlan), trying to take the lock as a Writer.
lockdep does not track readers for rwsems so the read wasn't obvious
from the reports.
On closer inspection the Reader holding the lock was conntrack looping
forever in nf_conntrack_cleanup_net_list(). Based on past experience
with occasional NIPA crashes I looked thru the tests which run before
the crash and noticed that the crash follows ip_defrag.sh. An immediate
red flag. Scouring thru (de)fragmentat
Wiz
CVE-2025-71120 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71120 [MEDIUM] CVE-2025-71120 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71120 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
SUNRPC: svcauth_gss: avoid NULL deref on zero length gss_token in gss_read_proxy_verf
A zero length gss_token results in pages == 0 and in_token->pages[0]
is NULL. The code unconditionally evaluates
page_address(in_token->pages[0]) for the initial memcpy, which can
dereference NULL even when the copy length is 0. Guard the first
memcpy so it only runs when length > 0.
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7
Wiz
CVE-2025-71081 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71081 [MEDIUM] CVE-2025-71081 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71081 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: stm32: sai: fix OF node leak on probe
The reference taken to the sync provider OF node when probing the
platform device is currently only dropped if the set_sync() callback
fails during DAI probe.
Make sure to drop the reference on platform probe failures (e.g. probe
deferral) and on driver unbind.
This also avoids a potential use-after-free in case the DAI is ever
reprobed without first rebinding the platform driver.
Source : NVD
## 5.5
Score
Published January 13, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV
Wiz
CVE-2023-54227 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54227 CVE-2023-54227 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54227 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blk-mq: fix tags leak when shrink nr_hw_queues
Although we don't need to realloc set->tags[] when shrink nr_hw_queues,
we need to free them. Or these tags will be leaked.
How to reproduce:
mount -t configfs configfs /mnt
modprobe null_blk nr_devices=0 submit_queues=8
mkdir /mnt/nullb/nullb0
echo 1 > /mnt/nullb/nullb0/power
echo 4 > /mnt/nullb/nullb0/submit_queues
rmdir /mnt/nullb/nullb0
In step 4, will alloc 9 tags (8 submit queues and 1 poll queue), then
in step 5, new_nr_hw_queues = 5 (4 submit queues and 1 poll queue).
At last in step 6, only these 5 tags are freed, the other 4 tags leaked.
Source : NVD
Published December 30, 2025
CNA
Wiz
CVE-2025-68746 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68746 CVE-2025-68746 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68746 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: tegra210-quad: Fix timeout handling
When the CPU that the QSPI interrupt handler runs on (typically CPU 0)
is excessively busy, it can lead to rare cases of the IRQ thread not
running before the transfer timeout is reached.
While handling the timeouts, any pending transfers are cleaned up and
the message that they correspond to is marked as failed, which leaves
the curr_xfer field pointing at stale memory.
To avoid this, clear curr_xfer to NULL upon timeout and check for this
condition when the IRQ thread is finally run.
While at it, also make sure to clear interrupts on failure so that new
interrupts can be run.
A better, more involved, fi
Wiz
CVE-2025-71073 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71073 [HIGH] CVE-2025-71073 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71073 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Input: lkkbd - disable pending work before freeing device
lkkbd_interrupt() schedules lk->tq via schedule_work(), and the work
handler lkkbd_reinit() dereferences the lkkbd structure and its
serio/input_dev fields.
lkkbd_disconnect() and error paths in lkkbd_connect() free the lkkbd
structure without preventing the reinit work from being queued again
until serio_close() returns. This can allow the work handler to run
after the structure has been freed, leading to a potential use-after-free.
Use disable_work_sync() instead of cancel_work_sync() to ensure the
reinit work cannot be re-queued, and call it both in lkkbd_disconnect()
and in lkkbd_connec
Wiz
CVE-2026-23190 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23190 [MEDIUM] CVE-2026-23190 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23190 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: amd: fix memory leak in acp3x pdm dma ops
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-socionext
kernel-uek-modules-extra
Sources
NVD
Debian 11, 12, 13, 14 Severity MEDIUM Has Fix Added at: Feb 15, 2026
Echo Severity MEDIUM Has Fix Added at: Feb 15, 2026
Red Hat 8, 9, 10 Severity LOW No Fix Added at: Feb 17, 2026
Ubuntu 16.0
Wiz
CVE-2022-50679 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50679 CVE-2022-50679 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50679 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i40e: Fix DMA mappings leak
During reallocation of RX buffers, new DMA mappings are created for
those buffers.
steps for reproduction:
while :
do
for ((i=0; i<=8160; i=i+32))
do
ethtool -G enp130s0f0 rx $i tx $i
sleep 0.5
ethtool -g enp130s0f0
done
done
This resulted in crash:
i40e 0000:01:00.1: Unable to allocate memory for the Rx descriptor ring, size=65536
Driver BUG
WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:141 xdp_rxq_info_unreg+0x43/0x50
Call Trace:
i40e_free_rx_resources+0x70/0x80 [i40e]
i40e_set_ringparam+0x27c/0x800 [i40e]
ethnl_set_rings+0x1b2/0x290
genl_family_rcv_msg_doit.isra.15+0x10f/0x150
genl_family_rcv_msg+0xb3/0x160
? rings_fil
Wiz
CVE-2026-23353 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23353 CVE-2026-23353 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23353 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: fix crash in ethtool offline loopback test
Since the conversion of ice to page pool, the ethtool loopback test
crashes:
BUG: kernel NULL pointer dereference, address: 000000000000000c
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 1100f1067 P4D 0
Oops: Oops: 0002 [#1] SMP NOPTI
CPU: 23 UID: 0 PID: 5904 Comm: ethtool Kdump: loaded Not tainted 6.19.0-0.rc7.260128g1f97d9dcf5364.49.eln154.x86_64 #1 PREEMPT(lazy)
Hardware name: [...]
RIP: 0010:ice_alloc_rx_bufs+0x1cd/0x310 [ice]
Code: 83 6c 24 30 01 66 41 89 47 08 0f 84 c0 00 00 00 41 0f b7 dc 48 8b 44 24 18 48 c1 e3 04 41 bb 00 10 00 00 48 8d 2c 18 8b 04
Wiz
CVE-2022-50751 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50751 CVE-2022-50751 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50751 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
configfs: fix possible memory leak in configfs_create_dir()
kmemleak reported memory leaks in configfs_create_dir():
unreferenced object 0xffff888009f6af00 (size 192):
comm "modprobe", pid 3777, jiffies 4295537735 (age 233.784s)
backtrace:
kmem_cache_alloc (mm/slub.c:3250 mm/slub.c:3256 mm/slub.c:3263 mm/slub.c:3273)
new_fragment (./include/linux/slab.h:600 fs/configfs/dir.c:163)
configfs_register_subsystem (fs/configfs/dir.c:1857)
basic_write (drivers/hwtracing/stm/p_basic.c:14) stm_p_basic
do_one_initcall (init/main.c:1296)
do_init_module (kernel/module/main.c:2455)
...
unreferenced object 0xffff888003ba7180 (size 96):
comm "modprobe", pid 3777,
Wiz
CVE-2025-68214 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2025-68214 [MEDIUM] CVE-2025-68214 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68214 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
timers: Fix NULL function pointer race in timer_shutdown_sync()
There is a race condition between timer_shutdown_sync() and timer
expiration that can lead to hitting a WARN_ON in expire_timers().
The issue occurs when timer_shutdown_sync() clears the timer function
to NULL while the timer is still running on another CPU. The race
scenario looks like this:
CPU0 CPU1 lock_timer_base()
expire_timers()
base->running_timer = timer;
unlock_timer_base()
[call_timer_fn enter]
mod_timer()
...
timer_shutdown_sync()
lock_timer_base()
// For now, will not detach the timer but only clear its function to NULL
if (base->running_timer != timer)
ret = detach_if_pe
Wiz
CVE-2025-71269 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71269 CVE-2025-71269 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71269 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: do not free data reservation in fallback from inline due to -ENOSPC
If we fail to create an inline extent due to -ENOSPC, we will attempt to
go through the normal COW path, reserve an extent, create an ordered
extent, etc. However we were always freeing the reserved qgroup data,
which is wrong since we will use data. Fix this by freeing the reserved
qgroup data in __cow_file_range_inline() only if we are not doing the
fallback (ret is <= 0).
Source : NVD
## 5.5
Score
Published March 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Releas
Wiz
CVE-2025-71202 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71202 [MEDIUM] CVE-2025-71202 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71202 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommu/sva: invalidate stale IOTLB entries for kernel address space
Introduce a new IOMMU interface to flush IOTLB paging cache entries for
the CPU kernel address space. This interface is invoked from the x86
architecture code that manages combined user and kernel page tables,
specifically before any kernel page table page is freed and reused.
This addresses the main issue with vfree() which is a common occurrence
and can be triggered by unprivileged users. While this resolves the
primary problem, it doesn't address some extremely rare case related to
memory unplug of memory that was present as reserved memory at boot, which
cannot be triggered by u
Wiz
CVE-2025-68259 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68259 CVE-2025-68259 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68259 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: SVM: Don't skip unrelated instruction if INT3/INTO is replaced
When re-injecting a soft interrupt from an INT3, INT0, or (select) INTn
instruction, discard the exception and retry the instruction if the code
stream is changed (e.g. by a different vCPU) between when the CPU
executes the instruction and when KVM decodes the instruction to get the
next RIP.
As effectively predicted by commit 6ef88d6e36c2 ("KVM: SVM: Re-inject
INT3/INTO instead of retrying the instruction"), failure to verify that
the correct INTn instruction was decoded can effectively clobber guest
state due to decoding the wrong instruction and thus specifying the
wrong next RI
Wiz
CVE-2025-71138 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71138 [MEDIUM] CVE-2025-71138 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71138 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm/dpu: Add missing NULL pointer check for pingpong interface
It is checked almost always in dpu_encoder_phys_wb_setup_ctl(), but in a
single place the check is missing.
Also use convenient locals instead of phys_enc->* where available.
Patchwork: https://patchwork.freedesktop.org/patch/693860/
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.2
Exploitation Probability (EPSS) N/A
Affected packages and librarie
Wiz
CVE-2025-68313 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68313 CVE-2025-68313 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68313 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/CPU/AMD: Add RDSEED fix for Zen5
There's an issue with RDSEED's 16-bit and 32-bit register output
variants on Zen5 which return a random value of 0 "at a rate inconsistent
with randomness while incorrectly signaling success (CF=1)". Search the
web for AMD-SB-7055 for more detail.
Add a fix glue which checks microcode revisions.
[ bp: Add microcode revisions checking, rewrite. ]
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Per
Wiz
CVE-2026-23466 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23466 CVE-2026-23466 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23466 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe: Open-code GGTT MMIO access protection
GGTT MMIO access is currently protected by hotplug (drm_dev_enter),
which works correctly when the driver loads successfully and is later
unbound or unloaded. However, if driver load fails, this protection is
insufficient because drm_dev_unplug() is never called.
Additionally, devm release functions cannot guarantee that all BOs with
GGTT mappings are destroyed before the GGTT MMIO region is removed, as
some BOs may be freed asynchronously by worker threads.
To address this, introduce an open-coded flag, protected by the GGTT
lock, that guards GGTT MMIO access. The flag is cleared during the
dev_fini_g
Wiz
CVE-2026-23000 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23000 [MEDIUM] CVE-2026-23000 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23000 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Fix crash on profile change rollback failure
mlx5e_netdev_change_profile can fail to attach a new profile and can
fail to rollback to old profile, in such case, we could end up with a
dangling netdev with a fully reset netdev_priv. A retry to change
profile, e.g. another attempt to call mlx5e_netdev_change_profile via
switchdev mode change, will crash trying to access the now NULL
priv->mdev.
This fix allows mlx5e_netdev_change_profile() to handle previous
failures and an empty priv, by not assuming priv is valid.
Pass netdev and mdev to all flows requiring
mlx5e_netdev_change_profile() and avoid passing priv.
In mlx5e_netdev_change_pro
Wiz
CVE-2025-71097 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71097 [MEDIUM] CVE-2025-71097 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71097 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv4: Fix reference count leak when using error routes with nexthop objects
When a nexthop object is deleted, it is marked as dead and then
fib_table_flush() is called to flush all the routes that are using the
dead nexthop.
The current logic in fib_table_flush() is to only flush error routes
(e.g., blackhole) when it is called as part of network namespace
dismantle (i.e., with flush_all=true). Therefore, error routes are not
flushed when their nexthop object is deleted:
## ip link add name dummy1 up type dummy
## ip nexthop add id 1 dev dummy1
## ip route add 198.51.100.1/32 nhid 1
## ip route add blackhole 198.51.100.2/32 nhid 1
## ip n
Wiz
CVE-2025-71116 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71116 [HIGH] CVE-2025-71116 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71116 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: make decode_pool() more resilient against corrupted osdmaps
If the osdmap is (maliciously) corrupted such that the encoded length
of ceph_pg_pool envelope is less than what is expected for a particular
encoding version, out-of-bounds reads may ensue because the only bounds
check that is there is based on that length value.
This patch adds explicit bounds checks for each field that is decoded
or skipped.
Source : NVD
## 7.1
Score
Published January 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Ex
Wiz
CVE-2025-68250 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68250 CVE-2025-68250 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68250 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hung_task: fix warnings caused by unaligned lock pointers
The blocker tracking mechanism assumes that lock pointers are at least
4-byte aligned to use their lower bits for type encoding.
However, as reported by Eero Tamminen, some architectures like m68k
only guarantee 2-byte alignment of 32-bit values. This breaks the
assumption and causes two related WARN_ON_ONCE checks to trigger.
To fix this, the runtime checks are adjusted to silently ignore any lock
that is not 4-byte aligned, effectively disabling the feature in such
cases and avoiding the related warnings.
Thanks to Geert Uytterhoeven for bisecting!
Source : NVD
Published December 16, 2
Wiz
CVE-2026-23234 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23234 [HIGH] CVE-2026-23234 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23234 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
f2fs: fix to avoid UAF in f2fs_write_end_io()
As syzbot reported an use-after-free issue in f2fs_write_end_io().
It is caused by below race condition:
loop device umount
worker_thread
loop_process_work
do_req_filebacked
blk_mq_end_request
blk_update_request
f2fs_write_end_io
dec_page_count
kill_f2fs_super
kill_block_super
f2fs_put_super
: free(sbi)
: get_pages(, F2FS_WB_CP_DATA)
accessed sbi which is freed
In kill_f2fs_super(), we will drop all page caches of f2fs inodes before
call free(sbi), it guarantee that all folios should end its writeback, so
it should be safe to access sbi before last folio_end_writeback().
Let's relocate ckp
Wiz
CVE-2026-23272 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23272 [HIGH] CVE-2026-23272 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23272 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: unconditionally bump set->nelems before insertion
In case that the set is full, a new element gets published then removed
without waiting for the RCU grace period, while RCU reader can be
walking over it already.
To address this issue, add the element transaction even if set is full,
but toggle the set_full flag to report -ENFILE so the abort path safely
unwinds the set to its previous state.
As for element updates, decrement set->nelems to restore it.
A simpler fix is to call synchronize_rcu() in the error path.
However, with a large batch adding elements to already maxed-out set,
this could cause noticeable slowdown of suc
Wiz
CVE-2023-54121 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54121 CVE-2023-54121 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54121 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix incorrect splitting in btrfs_drop_extent_map_range
In production we were seeing a variety of WARN_ON()'s in the extent_map
code, specifically in btrfs_drop_extent_map_range() when we have to call
add_extent_mapping() for our second split.
Consider the following extent map layout
PINNED
[0 16K) [32K, 48K)
and then we call btrfs_drop_extent_map_range for [0, 36K), with
skip_pinned == true. The initial loop will have
start = 0
end = 36K
len = 36K
we will find the [0, 16k) extent, but since we are pinned we will skip
it, which has this code
start = em_end;
if (end != (u64)-1)
len = start + len - em_end;
em_end here is 16K, so now the v
Wiz
CVE-2023-54216 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54216 CVE-2023-54216 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54216 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: TC, Fix using eswitch mapping in nic mode
Cited patch is using the eswitch object mapping pool while
in nic mode where it isn't initialized. This results in the
trace below 0 .
Fix that by using either nic or eswitch object mapping pool
depending if eswitch is enabled or not.
[ 826.446729] BUG: KASAN: slab-use-after-free in mlx5_add_flow_rules+0x30/0x490 [mlx5_core]
[ 826.447515] Read of size 8 at addr ffff888194485830 by task tc/6233
[ 826.448243] CPU: 16 PID: 6233 Comm: tc Tainted: G W 6.3.0-rc6+ #1
[ 826.448890] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 826.449
Wiz
CVE-2023-54058 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54058 CVE-2023-54058 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54058 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
firmware: arm_ffa: Check if ffa_driver remove is present before executing
Currently ffa_drv->remove() is called unconditionally from
ffa_device_remove(). Since the driver registration doesn't check for it
and allows it to be registered without .remove callback, we need to check
for the presence of it before executing it from ffa_device_remove() to
above a NULL pointer dereference like the one below:
| Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
| Mem abort info:
| ESR = 0x0000000086000004
| EC = 0x21: IABT (current EL), IL = 32 bits
| SET = 0, FnV = 0
| EA = 0, S1PTW = 0
| FSC = 0x04: level 0 translation fau
Wiz
CVE-2023-54311 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54311 CVE-2023-54311 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54311 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: fix deadlock when converting an inline directory in nojournal mode
In no journal mode, ext4_finish_convert_inline_dir() can self-deadlock
by calling ext4_handle_dirty_dirblock() when it already has taken the
directory lock. There is a similar self-deadlock in
ext4_incvert_inline_data_nolock() for data files which we'll fix at
the same time.
A simple reproducer demonstrating the problem:
mke2fs -Fq -t ext2 -O inline_data -b 4k /dev/vdc 64
mount -t ext4 -o dirsync /dev/vdc /vdc
cd /vdc
mkdir file0
cd file0
touch file0
touch file1
attr -s BurnSpaceInEA -V abcde .
touch supercalifragilisticexpialidocious
Source : NVD
Published December 30, 202
Wiz
CVE-2023-54010 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54010 CVE-2023-54010 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54010 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ACPICA: ACPICA: check null return of ACPI_ALLOCATE_ZEROED in acpi_db_display_objects
ACPICA commit 0d5f467d6a0ba852ea3aad68663cbcbd43300fd4
ACPI_ALLOCATE_ZEROED may fails, object_info might be null and will cause
null pointer dereference later.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-core
kernel-rt-64k-modules
Sources
NVD
Debian 11, 12, 13, 14 Has F
Wiz
CVE-2025-68727 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68727 CVE-2025-68727 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68727 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ntfs3: Fix uninit buffer allocated by __getname()
Fix uninit errors caused after buffer allocation given to 'de'; by
initializing the buffer with zeroes. The fix was found by using KMSAN.
Source : NVD
## 3.3
Score
Published December 24, 2025
Severity LOW
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-default-devel
linux-gcp-6.8
Sources
NVD
Container-Optimized OS Has Fix Added at: Jan 22, 2026
Debia
Wiz
CVE-2023-54263 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54263 CVE-2023-54263 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54263 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/nouveau/kms/nv50-: init hpd_irq_lock for PIOR DP
Fixes OOPS on boards with ANX9805 DP encoders.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-tools-libs-devel
kernel-default-devel
Sources
NVD
Debian 11, 12 No Fix Added at: Dec 31, 2025
Debian 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity MEDIUM Has Fix Added at
Wiz
CVE-2026-23123 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23123 [MEDIUM] CVE-2026-23123 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23123 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
interconnect: debugfs: initialize src_node and dst_node to empty strings
The debugfs_create_str() API assumes that the string pointer is either NULL
or points to valid kmalloc() memory. Leaving the pointer uninitialized can
cause problems.
Initialize src_node and dst_node to empty strings before creating the
debugfs entries to guarantee that reads and writes are safe.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3
Wiz
CVE-2023-54224 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54224 CVE-2023-54224 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54224 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix lockdep splat and potential deadlock after failure running delayed items
When running delayed items we are holding a delayed node's mutex and then
we will attempt to modify a subvolume btree to insert/update/delete the
delayed items. However if have an error during the insertions for example,
btrfs_insert_delayed_items() may return with a path that has locked extent
buffers (a leaf at the very least), and then we attempt to release the
delayed node at __btrfs_run_delayed_items(), which requires taking the
delayed node's mutex, causing an ABBA type of deadlock. This was reported
by syzbot and the lockdep splat is the following:
## WARNIN
Wiz
CVE-2025-68770 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68770 CVE-2025-68770 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68770 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: Fix XDP_TX path
For XDP_TX action in bnxt_rx_xdp(), clearing of the event flags is not
correct. __bnxt_poll_work() -> bnxt_rx_pkt() -> bnxt_rx_xdp() may be
looping within NAPI and some event flags may be set in earlier
iterations. In particular, if BNXT_TX_EVENT is set earlier indicating
some XDP_TX packets are ready and pending, it will be cleared if it is
XDP_TX action again. Normally, we will set BNXT_TX_EVENT again when we
successfully call __bnxt_xmit_xdp(). But if the TX ring has no more
room, the flag will not be set. This will cause the TX producer to be
ahead but the driver will not hit the TX doorbell.
For multi-buf XDP_TX, there
Wiz
CVE-2026-23135 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23135 [MEDIUM] CVE-2026-23135 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23135 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath12k: fix dma_free_coherent() pointer
dma_alloc_coherent() allocates a DMA mapped buffer and stores the
addresses in XXX_unaligned fields. Those should be reused when freeing
the buffer rather than the aligned addresses.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kselftests-kmp-azure
kernel-azure-devel
Sources
NVD
CBL-Mariner 3.0
Wiz
CVE-2025-68380 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68380 CVE-2025-68380 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68380 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: fix peer HE MCS assignment
In ath11k_wmi_send_peer_assoc_cmd(), peer's transmit MCS is sent to
firmware as receive MCS while peer's receive MCS sent as transmit MCS,
which goes against firmwire's definition.
While connecting to a misbehaved AP that advertises 0xffff (meaning not
supported) for 160 MHz transmit MCS map, firmware crashes due to 0xffff
is assigned to he_mcs->rx_mcs_set field.
Ext Tag: HE Capabilities
[...]
Supported HE-MCS and NSS Set
[...]
Rx and Tx MCS Maps 160 MHz
[...]
Tx HE-MCS Map 160 MHz: 0xffff
Swap the assignment to fix this issue.
As the HE rate control mask is meant to limit our own transmit MCS, it
needs t
Wiz
CVE-2022-50710 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50710 CVE-2022-50710 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50710 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: set tx_tstamps when creating new Tx rings via ethtool
When the user changes the number of queues via ethtool, the driver
allocates new rings. This allocation did not initialize tx_tstamps. This
results in the tx_tstamps field being zero (due to kcalloc allocation), and
would result in a NULL pointer dereference when attempting a transmit
timestamp on the new ring.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS)
Wiz
CVE-2023-53859 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53859 CVE-2023-53859 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53859 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/idle: mark arch_cpu_idle() noinstr
linux-next commit ("cpuidle: tracing: Warn about !rcu_is_watching()")
adds a new warning which hits on s390's arch_cpu_idle() function:
RCU not on for: arch_cpu_idle+0x0/0x28
WARNING: CPU: 2 PID: 0 at include/linux/trace_recursion.h:162 arch_ftrace_ops_list_func+0x24c/0x258
Modules linked in:
CPU: 2 PID: 0 Comm: swapper/2 Not tainted 6.2.0-rc6-next-20230202 #4
Hardware name: IBM 8561 T01 703 (z/VM 7.3.0)
Krnl PSW : 0404d00180000000 00000000002b55c0 (arch_ftrace_ops_list_func+0x250/0x258)
R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:1 PM:0 RI:0 EA:3
Krnl GPRS: c0000000ffffbfff 0000000080000002 0000000000000026
Wiz
CVE-2026-23351 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23351 [HIGH] CVE-2026-23351 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23351 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_set_pipapo: split gc into unlink and reclaim phase
Yiming Qian reports Use-after-free in the pipapo set type:
Under a large number of expired elements, commit-time GC can run for a very
long time in a non-preemptible context, triggering soft lockup warnings and
RCU stall reports (local denial of service).
We must split GC in an unlink and a reclaim phase.
We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.
call_rcu() does not protect us: dump operations or element lookups starting
after call_r
Wiz
CVE-2026-23231 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23231 [HIGH] CVE-2026-23231 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23231 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: fix use-after-free in nf_tables_addchain()
nf_tables_addchain() publishes the chain to table->chains via
list_add_tail_rcu() (in nft_chain_add()) before registering hooks.
If nf_tables_register_hook() then fails, the error path calls
nft_chain_del() (list_del_rcu()) followed by nf_tables_chain_destroy()
with no RCU grace period in between.
This creates two use-after-free conditions:
Control-plane: nf_tables_dump_chains() traverses table->chains
under rcu_read_lock(). A concurrent dump can still be walking
the chain when the error path frees it.
Packet path: for NFPROTO_INET, nf_register_net_hook() briefly
installs the IPv4 h
Wiz
CVE-2026-23033 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23033 CVE-2026-23033 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23033 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: omap-dma: fix dma_pool resource leak in error paths
The dma_pool created by dma_pool_create() is not destroyed when
dma_async_device_register() or of_dma_controller_register() fails,
causing a resource leak in the probe error paths.
Add dma_pool_destroy() in both error paths to properly release the
allocated dma_pool resource.
Source : NVD
Published January 31, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 2.8
Exploitation Probability (EPSS) N/A
Affected packages and li
Wiz
CVE-2026-23010 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23010 [HIGH] CVE-2026-23010 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23010 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: Fix use-after-free in inet6_addr_del().
syzbot reported use-after-free of inet6_ifaddr in
inet6_addr_del(). 0
The cited commit accidentally moved ipv6_del_addr() for
mngtmpaddr before reading its ifp->flags for temporary
addresses in inet6_addr_del().
Let's move ipv6_del_addr() down to fix the UAF.
CPU: 0 UID: 0 PID: 9593 Comm: syz.3.1618 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
Call Trace: __dump_stack lib/dump_stack.c:94 [inline]
dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
print_address_description mm/kasan/report.c:378 [inline]
print_report+0xcd/0
Wiz
CVE-2026-31394 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31394 CVE-2026-31394 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31394 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations
ieee80211_chan_bw_change() iterates all stations and accesses
link->reserved.oper via sta->sdata->link[link_id]. For stations on
AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to
the VLAN sdata, whose link never participates in chanctx reservations.
This leaves link->reserved.oper zero-initialized with chan == NULL,
causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw()
when accessing chandef->chan->band during CSA.
Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata()
before accessing link data.
[also change sta->sdata in ARRAY_SIZE even
Wiz
CVE-2022-50865 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50865 CVE-2022-50865 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50865 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tcp: fix a signed-integer-overflow bug in tcp_add_backlog()
The type of sk_rcvbuf and sk_sndbuf in struct sock is int, and
in tcp_add_backlog(), the variable limit is caculated by adding
sk_rcvbuf, sk_sndbuf and 64 * 1024, it may exceed the max value
of int and overflow. This patch reduces the limit budget by
halving the sndbuf to solve this issue since ACK packets are much
smaller than the payload.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Rocky Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Wiz
CVE-2022-50863 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50863 CVE-2022-50863 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50863 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtw89: free unused skb to prevent memory leak
This avoid potential memory leak under power saving mode.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-modules-core
kernel-rt-debug-modules-extra
Sources
NVD
Debian 11 No Fix Added at: Dec 31, 2025
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 8 Severity
Wiz
CVE-2025-68302 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68302 CVE-2025-68302 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68302 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: sxgbe: fix potential NULL dereference in sxgbe_rx()
Currently, when skb is null, the driver prints an error and then
dereferences skb on the next line.
To fix this, let's add a 'break' after the error message to switch
to sxgbe_rx_refill(), which is similar to the approach taken by the
other drivers in this particular case, e.g. calxeda with xgmac_rx().
Found during a code review.
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability
Wiz
CVE-2025-71114 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71114 [MEDIUM] CVE-2025-71114 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71114 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
via_wdt: fix critical boot hang due to unnamed resource allocation
The VIA watchdog driver uses allocate_resource() to reserve a MMIO
region for the watchdog control register. However, the allocated
resource was not given a name, which causes the kernel resource tree
to contain an entry marked as " " under /proc/iomem on x86
platforms.
During boot, this unnamed resource can lead to a critical hang because
subsequent resource lookups and conflict checks fail to handle the
invalid entry properly.
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Ex
Wiz
CVE-2022-50878 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50878 CVE-2022-50878 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50878 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gpu: lontium-lt9611: Fix NULL pointer dereference in lt9611_connector_init()
A NULL check for bridge->encoder shows that it may be NULL, but it
already been dereferenced on all paths leading to the check.
812 if (!bridge->encoder) {
Dereference the pointer bridge->encoder.
810 drm_connector_attach_encoder( connector, bridge->encoder);
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libr
Wiz
CVE-2023-54098 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54098 CVE-2023-54098 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54098 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915/gvt: fix gvt debugfs destroy
When gvt debug fs is destroyed, need to have a sane check if drm
minor's debugfs root is still available or not, otherwise in case like
device remove through unbinding, drm minor's debugfs directory has
already been removed, then intel_gvt_debugfs_clean() would act upon
dangling pointer like below oops.
i915 0000:00:02.0: Direct firmware load for i915/gvt/vid_0x8086_did_0x1926_rid_0x0a.golden_hw_state failed with error -2
i915 0000:00:02.0: MDEV: Registered
Console: switching to colour dummy device 80x25
i915 0000:00:02.0: MDEV: Unregistering
BUG: kernel NULL pointer dereference, address: 00000000000000a0
PGD 0
Wiz
CVE-2025-68223 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68223 [MEDIUM] CVE-2025-68223 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68223 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/radeon: delete radeon_fence_process in is_signaled, no deadlock
Delete the attempt to progress the queue when checking if fence is
signaled. This avoids deadlock.
dma-fence_ops::signaled can be called with the fence lock in unknown
state. For radeon, the fence lock is also the wait queue lock. This can
cause a self deadlock when signaled() tries to make forward progress on
the wait queue. But advancing the queue is unneeded because incorrectly
returning false from signaled() is perfectly acceptable.
(cherry picked from commit 527ba26e50ec2ca2be9c7c82f3ad42998a75d0db)
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
Wiz
CVE-2023-54283 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54283 CVE-2023-54283 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54283 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Address KCSAN report on bpf_lru_list
KCSAN reported a data-race when accessing node->ref.
Although node->ref does not have to be accurate,
take this chance to use a more common READ_ONCE() and WRITE_ONCE()
pattern instead of data_race().
There is an existing bpf_lru_node_is_ref() and bpf_lru_node_set_ref().
This patch also adds bpf_lru_node_clear_ref() to do the
WRITE_ONCE(node->ref, 0) also.
BUG: KCSAN: data-race in __bpf_lru_list_rotate / __htab_lru_percpu_map_update_elem
write to 0xffff888137038deb of 1 bytes by task 11240 on cpu 1:
__bpf_lru_node_move kernel/bpf/bpf_lru_list.c:113 [inline]
__bpf_lru_list_rotate_active kernel/bpf/bpf_lru_
Wiz
CVE-2026-23062 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23062 [MEDIUM] CVE-2026-23062 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23062 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: hp-bioscfg: Fix kernel panic in GET_INSTANCE_ID macro
The GET_INSTANCE_ID macro that caused a kernel panic when accessing sysfs
attributes:
Off-by-one error: The loop condition used 'name
without checking if attr_name_kobj was NULL, causing a null pointer
dereference in min_length_show() and other attribute show functions.
The panic occurred when fwupd tried to read BIOS configuration attributes:
Oops: general protection fault [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:min_length_show+0xcf/0x1d0 [hp_bioscfg]
Add a NULL check for attr_name_kobj before dereferencing and corre
Wiz
CVE-2023-53831 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53831 CVE-2023-53831 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53831 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: read sk->sk_family once in sk_mc_loop()
syzbot is playing with IPV6_ADDRFORM quite a lot these days,
and managed to hit the WARN_ON_ONCE(1) in sk_mc_loop()
We have many more similar issues to fix.
WARNING: CPU: 1 PID: 1593 at net/core/sock.c:782 sk_mc_loop+0x165/0x260
Modules linked in:
CPU: 1 PID: 1593 Comm: kworker/1:3 Not tainted 6.1.40-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
Workqueue: events_power_efficient gc_worker
RIP: 0010:sk_mc_loop+0x165/0x260 net/core/sock.c:782
Code: 34 1b fd 49 81 c7 18 05 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 20 00 74 08 4c 89 ff e8 25 36 6d fd 4d 8b
Wiz
CVE-2026-23248 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23248 [HIGH] CVE-2026-23248 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23248 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/core: Fix refcount bug and potential UAF in perf_mmap
Syzkaller reported a refcount_t: addition on 0; use-after-free warning
in perf_mmap.
The issue is caused by a race condition between a failing mmap() setup
and a concurrent mmap() on a dependent event (e.g., using output
redirection).
In perf_mmap(), the ring_buffer (rb) is allocated and assigned to
event->rb with the mmap_mutex held. The mutex is then released to
perform map_range().
If map_range() fails, perf_mmap_close() is called to clean up.
However, since the mutex was dropped, another thread attaching to
this event (via inherited events or output redirection) can acquire
the mutex,
Wiz
CVE-2025-40331 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40331 CVE-2025-40331 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40331 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sctp: Prevent TOCTOU out-of-bounds write
For the following path not holding the sock lock,
sctp_diag_dump() -> sctp_for_each_endpoint() -> sctp_ep_dump()
make sure not to exceed bounds in case the address list has grown
between buffer allocation (time-of-check) and write (time-of-use).
Source : NVD
## 6.4
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-ue
Wiz
CVE-2025-68238 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68238 CVE-2025-68238 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68238 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mtd: rawnand: cadence: fix DMA device NULL pointer dereference
dma_dev
cdns_ctrl->dmac
dma_dev
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
linux-raspi
kernel-kvmsmall-vdso
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 17, 2025
Echo Has Fix Added at: Dec 17, 2025
Ubuntu 20.04, 22.04, 24.04, 25.10 Severity MEDIUM Has Fix Added at: Dec 18, 2025
## Get a C
Wiz
CVE-2023-54029 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54029 CVE-2023-54029 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54029 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-kvm
kernel-rt-modules-core
Sources
NVD
Debian 11 No Fix Added at: Dec 26, 2025
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 7, 8, 9 Severity MEDIUM No Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Dec 2
Wiz
CVE-2025-71225 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.3
CVE-2025-71225 [MEDIUM] CVE-2025-71225 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71225 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md: suspend array while updating raid_disks via sysfs
In raid1_reshape(), freeze_array() is called before modifying the r1bio
memory pool (conf->r1bio_pool) and conf->raid_disks, and
unfreeze_array() is called after the update is completed.
However, freeze_array() only waits until nr_sync_pending and
(nr_pending - nr_queued) of all buckets reaches zero. When an I/O error
occurs, nr_queued is increased and the corresponding r1bio is queued to
either retry_list or bio_end_io_list. As a result, freeze_array() may
unblock before these r1bios are released.
This can lead to a situation where conf->raid_disks and the mempool have
already been updated whi
Wiz
CVE-2022-50739 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50739 CVE-2022-50739 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50739 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Add null pointer check for inode operations
This adds a sanity check for the i_op pointer of the inode which is
returned after reading Root directory MFT record. We should check the
i_op is valid before trying to create the root dentry, otherwise we may
encounter a NPD while mounting a image with a funny Root directory MFT
record.
[ 114.484325] BUG: kernel NULL pointer dereference, address: 0000000000000008
[ 114.484811] #PF: supervisor read access in kernel mode
[ 114.485084] #PF: error_code(0x0000) - not-present page
[ 114.485606] PGD 0 P4D 0
[ 114.485975] Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI
[ 114.486570] CPU: 0 PID: 237 Comm: mount
Wiz
CVE-2025-1272 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.7
CVE-2025-1272 [HIGH] CVE-2025-1272 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-1272 :
Linux Kernel vulnerability analysis and mitigation
The Linux Kernel lockdown mode for kernel versions starting on 6.12 and above for Fedora Linux has the lockdown mode disabled without any warning. This may allow an attacker to gain access to sensitive information such kernel memory mappings, I/O ports, BPF and kprobes. Additionally unsigned modules can be loaded, leading to execution of untrusted code breaking breaking any Secure Boot protection. This vulnerability affects only Fedora Linux.
Source : NVD
## 7.7
Score
Published February 18, 2026
Severity HIGH
CNA Score 7.7
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS
Wiz
CVE-2025-40344 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40344 CVE-2025-40344 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40344 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: Intel: avs: Disable periods-elapsed work when closing PCM
avs_dai_fe_shutdown() handles the shutdown procedure for HOST HDAudio
stream while period-elapsed work services its IRQs. As the former
frees the DAI's private context, these two operations shall be
synchronized to avoid slab-use-after-free or worse errors.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek
Wiz
CVE-2025-68228 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68228 CVE-2025-68228 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68228 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/plane: Fix create_in_format_blob() return value
create_in_format_blob() is either supposed to return a valid
pointer or an error, but never NULL. The caller will dereference
the blob when it is not an error, and thus will oops if NULL
returned. Return proper error values in the failure cases.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-devel-matched
kernel-r
Wiz
CVE-2026-23239 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23239 [HIGH] CVE-2026-23239 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23239 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
espintcp: Fix race condition in espintcp_close()
This issue was discovered during a code audit.
After cancel_work_sync() is called from espintcp_close(),
espintcp_tx_work() can still be scheduled from paths such as
the Delayed ACK handler or ksoftirqd.
As a result, the espintcp_tx_work() worker may dereference a
freed espintcp ctx or sk.
The following is a simple race scenario:
cpu0 cpu1
espintcp_close()
cancel_work_sync(&ctx->work);
espintcp_write_space()
schedule_work(&ctx->work);
To prevent this race condition, cancel_work_sync() is
replaced with disable_work_sync().
Source : NVD
## 7.8
Score
Published March 10, 2026
Severity HIGH
CN
Wiz
CVE-2025-68735 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68735 CVE-2025-68735 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68735 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/panthor: Prevent potential UAF in group creation
This commit prevents the possibility of a use after free issue in the
GROUP_CREATE ioctl function, which arose as pointer to the group is
accessed in that ioctl function after storing it in the Xarray.
A malicious userspace can second guess the handle of a group and try
to call GROUP_DESTROY ioctl from another thread around the same time
as GROUP_CREATE ioctl.
To prevent the use after free exploit, this commit uses a mark on an
entry of group pool Xarray which is added just before returning from
the GROUP_CREATE ioctl function. The mark is checked for all ioctls
that specify the group handle and
Wiz
CVE-2026-23287 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23287 CVE-2026-23287 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23287 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
irqchip/sifive-plic: Fix frozen interrupt due to affinity setting
PLIC ignores interrupt completion message for disabled interrupt, explained
by the specification:
The PLIC signals it has completed executing an interrupt handler by
writing the interrupt ID it received from the claim to the
claim/complete register. The PLIC does not check whether the completion
ID is the same as the last claim ID for that target. If the completion
ID does not match an interrupt source that is currently enabled for
the target, the completion is silently ignored.
This caused problems in the past, because an interrupt can be disabled
while still being handled and plic
Wiz
CVE-2023-54044 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54044 CVE-2023-54044 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54044 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spmi: Add a check for remove callback when removing a SPMI driver
When removing a SPMI driver, there can be a crash due to NULL pointer
dereference if it does not have a remove callback defined. This is
one such call trace observed when removing the QCOM SPMI PMIC driver:
dump_backtrace.cfi_jt+0x0/0x8
dump_stack_lvl+0xd8/0x16c
panic+0x188/0x498
__cfi_slowpath+0x0/0x214
__cfi_slowpath+0x1dc/0x214
spmi_drv_remove+0x16c/0x1e0
device_release_driver_internal+0x468/0x79c
driver_detach+0x11c/0x1a0
bus_remove_driver+0xc4/0x124
driver_unregister+0x58/0x84
cleanup_module+0x1c/0xc24 [qcom_spmi_pmic]
__do_sys_delete_module+0x3ec/0x53c
__arm64_sys_delete_module
Wiz
CVE-2025-68256 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68256 CVE-2025-68256 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68256 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8723bs: fix out-of-bounds read in rtw_get_ie() parser
The Information Element (IE) parser rtw_get_ie() trusted the length
byte of each IE without validating that the IE body (len bytes after
the 2-byte header) fits inside the remaining frame buffer. A malformed
frame can advertise an IE length larger than the available data, causing
the parser to increment its pointer beyond the buffer end. This results
in out-of-bounds reads or, depending on the pattern, an infinite loop.
Fix by validating that (offset + 2 + len) does not exceed the limit
before accepting the IE or advancing to the next element.
This prevents OOB reads and ensures the
Wiz
CVE-2023-54314 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54314 CVE-2023-54314 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54314 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: af9005: Fix null-ptr-deref in af9005_i2c_xfer
In af9005_i2c_xfer, msg is controlled by user. When msg[i].buf
is null and msg[i].len is zero, former checks on msg[i].buf would be
passed. Malicious data finally reach af9005_i2c_xfer. If accessing
msg[i].buf[0] without sanity check, null ptr deref would happen.
We add check on msg[i].len to prevent crash.
Similar commit:
commit 0ed554fd769a
("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA
Wiz
CVE-2026-23161 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.3
CVE-2026-23161 [HIGH] CVE-2026-23161 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23161 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/shmem, swap: fix race of truncate and swap entry split
The helper for shmem swap freeing is not handling the order of swap
entries correctly. It uses xa_cmpxchg_irq to erase the swap entry, but it
gets the entry order before that using xa_get_order without lock
protection, and it may get an outdated order value if the entry is split
or changed in other ways after the xa_get_order and before the
xa_cmpxchg_irq.
And besides, the order could grow and be larger than expected, and cause
truncation to erase data beyond the end border. For example, if the
target entry and following entries are swapped in or freed, then a large
folio was added in place
Wiz
CVE-2026-23253 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23253 [HIGH] CVE-2026-23253 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23253 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: dvb-core: fix wrong reinitialization of ringbuffer on reopen
dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the
DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which
reinitializes the waitqueue list head to empty.
Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the
same DVR device share it), this orphans any existing waitqueue entries
from io_uring poll or epoll, leaving them with stale prev/next pointers
while the list head is reset to {self, self}.
The waitqueue and spinlock in dvr_buffer are already properly
initialized once in dvb_dmxdev_init(). The open path only needs to
reset the
Wiz
CVE-2026-23340 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23340 [HIGH] CVE-2026-23340 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23340 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs
When shrinking the number of real tx queues,
netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush
qdiscs for queues which will no longer be used.
qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with
qdisc_lock(). However, for lockless qdiscs, the dequeue path is
serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so
qdisc_reset() can run concurrently with __qdisc_run() and free skbs
while they are still being dequeued, leading to UAF.
This can easily be reproduced on e.g. virtio-net by imposing heavy
traffic while frequently chan
Wiz
CVE-2025-68234 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68234 CVE-2025-68234 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68234 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/cmd_net: fix wrong argument types for skb_queue_splice()
If timestamp retriving needs to be retried and the local list of
SKB's already has entries, then it's spliced back into the socket
queue. However, the arguments for the splice helper are transposed,
causing exactly the wrong direction of splicing into the on-stack
list. Fix that up.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packa
Wiz
CVE-2026-23110 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23110 [MEDIUM] CVE-2026-23110 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23110 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: core: Wake up the error handler when final completions race against each other
The fragile ordering between marking commands completed or failed so
that the error handler only wakes when the last running command
completes or times out has race conditions. These race conditions can
cause the SCSI layer to fail to wake the error handler, leaving I/O
through the SCSI host stuck as the error state cannot advance.
First, there is an memory ordering issue within scsi_dec_host_busy().
The write which clears SCMD_STATE_INFLIGHT may be reordered with reads
counting in scsi_host_busy(). While the local CPU will see its own
write, reordering can allow o
Wiz
CVE-2022-50821 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50821 CVE-2022-50821 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50821 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
SUNRPC: Don't leak netobj memory when gss_read_proxy_verf() fails
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
python-perf
kernel-doc
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6, 7, 8, 9 Severity MEDIUM No Fix Added at: Dec 31, 2025
Ubuntu 14.04, 22.04 Severity MEDIUM Has Fix Added at: Jan 05, 2026
U
Wiz
CVE-2025-71075 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71075 [HIGH] CVE-2025-71075 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71075 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: aic94xx: fix use-after-free in device removal path
The asd_pci_remove() function fails to synchronize with pending tasklets
before freeing the asd_ha structure, leading to a potential
use-after-free vulnerability.
When a device removal is triggered (via hot-unplug or module unload),
race condition can occur.
The fix adds tasklet_kill() before freeing the asd_ha structure,
ensuring all scheduled tasklets complete before cleanup proceeds.
Source : NVD
## 7.8
Score
Published January 13, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Dat
Wiz
CVE-2025-68335 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68335 CVE-2025-68335 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68335 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
comedi: pcl818: fix null-ptr-deref in pcl818_ai_cancel()
Syzbot identified an issue [1] in pcl818_ai_cancel(), which stems from
the fact that in case of early device detach via pcl818_detach(),
subdevice dev->read_subdev may not have initialized its pointer to
&struct comedi_async as intended. Thus, any such dereferencing of
&s->async->cmd will lead to general protection fault and kernel crash.
Mitigate this problem by removing a call to pcl818_ai_cancel() from
pcl818_detach() altogether. This way, if the subdevice setups its
support for async commands, everything async-related will be
handled via subdevice's own ->cancel() function in
comedi_devic
Wiz
CVE-2025-71085 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71085 [MEDIUM] CVE-2025-71085 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71085 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: BUG() in pskb_expand_head() as part of calipso_skbuff_setattr()
There exists a kernel oops caused by a BUG_ON(nhead INT_MAX
(i.e. (int)(skb_headroom(skb) + len_delta) skb_headroom(skb)) is meant to ensure
that delta = headroom - skb_headroom(skb) is never negative, otherwise
we will trigger a BUG_ON in pskb_expand_head(). However, if
headroom > INT_MAX and delta cmsg_len = cmsg_len;
cmsg->cmsg_level = IPPROTO_IPV6;
cmsg->cmsg_type = IPV6_HOPOPTS;
char * hop_hdr = (char *)cmsg + sizeof(struct cmsghdr);
hop_hdr[1] = 0x9; //set hop size - (0x9 + 1) * 8 = 80
sendmsg(fd, &msg, 0);
Source : NVD
## 5.5
Score
Published January 13, 2026
Severit
Wiz
CVE-2025-40359 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40359 CVE-2025-40359 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40359 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/x86/intel: Fix KASAN global-out-of-bounds warning
When running "perf mem record" command on CWF, the below KASAN
global-out-of-bounds warning is seen.
BUG: KASAN: global-out-of-bounds in cmt_latency_data+0x176/0x1b0
Read of size 4 at addr ffffffffb721d000 by task dtlb/9850
Call Trace:
kasan_report+0xb8/0xf0
cmt_latency_data+0x176/0x1b0
setup_arch_pebs_sample_data+0xf49/0x2560
intel_pmu_drain_arch_pebs+0x577/0xb00
handle_pmi_common+0x6c4/0xc80
The issue is caused by below code in __grt_latency_data(). The code
tries to access x86_hybrid_pmu structure which doesn't exist on
non-hybrid platform like CWF.
WARN_ON_ONCE(hybrid_pmu(event->pmu)->p
Wiz
CVE-2023-54297 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54297 CVE-2023-54297 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54297 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: zoned: fix memory leak after finding block group with super blocks
At exclude_super_stripes(), if we happen to find a block group that has
super blocks mapped to it and we are on a zoned filesystem, we error out
as this is not supposed to happen, indicating either a bug or maybe some
memory corruption for example. However we are exiting the function without
freeing the memory allocated for the logical address of the super blocks.
Fix this by freeing the logical address.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release
Wiz
CVE-2023-54267 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54267 CVE-2023-54267 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54267 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/pseries: Rework lppaca_shared_proc() to avoid DEBUG_PREEMPT
lppaca_shared_proc() takes a pointer to the lppaca which is typically
accessed through get_lppaca(). With DEBUG_PREEMPT enabled, this leads
to checking if preemption is enabled, for example:
BUG: using smp_processor_id() in preemptible [00000000] code: grep/10693
caller is lparcfg_data+0x408/0x19a0
CPU: 4 PID: 10693 Comm: grep Not tainted 6.5.0-rc3 #2
Call Trace:
dump_stack_lvl+0x154/0x200 (unreliable)
check_preemption_disabled+0x214/0x220
lparcfg_data+0x408/0x19a0
...
This isn't actually a problem however, as it does not matter which
lppaca is accessed, the shared proc state will
Wiz
CVE-2023-54011 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54011 CVE-2023-54011 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54011 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: mpi3mr: Fix an issue found by KASAN
Write only correct size (32 instead of 64 bytes).
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug-devel-matched
kernel-rt-debug-kvm
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 8 Severity LOW Has Fix Added at: Dec 26, 2025
Red Hat 9 Severity LOW Has
Wiz
CVE-2023-53852 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53852 CVE-2023-53852 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53852 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-core: fix memory leak in dhchap_secret_store
Free dhchap_secret in nvme_ctrl_dhchap_secret_store() before we return
fix following kmemleack:-
unreferenced object 0xffff8886376ea800 (size 64):
comm "check", pid 22048, jiffies 4344316705 (age 92.199s)
hex dump (first 32 bytes):
44 48 48 43 2d 31 3a 30 30 3a 6e 78 72 35 4b 67 DHHC-1:00:nxr5Kg
75 58 34 75 6f 41 78 73 4a 61 34 63 2f 68 75 4c uX4uoAxsJa4c/huL
backtrace:
[] __kmalloc+0x4b/0x130
[] nvme_ctrl_dhchap_secret_store+0x8f/0x160 [nvme_core]
[] kernfs_fop_write_iter+0x12b/0x1c0
[] vfs_write+0x2ba/0x3c0
[] ksys_write+0x5f/0xe0
[] do_syscall_64+0x3b/0x90
[] entry_SYSCALL_64_after_hwframe+0x72/0
Wiz
CVE-2026-23042 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23042 CVE-2026-23042 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23042 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: fix aux device unplugging when rdma is not supported by vport
If vport flags do not contain VIRTCHNL2_VPORT_ENABLE_RDMA, driver does not
allocate vdev_info for this vport. This leads to kernel NULL pointer
dereference in idpf_idc_vport_dev_down(), which references vdev_info for
every vport regardless.
Check, if vdev_info was ever allocated before unplugging aux device.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.3
Exploitation Probabilit
Wiz
CVE-2025-68352 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68352 CVE-2025-68352 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68352 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: ch341: fix out-of-bounds memory access in ch341_transfer_one
Discovered by Atuin - Automated Vulnerability Discovery Engine.
The 'len' variable is calculated as 'min(32, trans->len + 1)',
which includes the 1-byte command header.
When copying data from 'trans->tx_buf' to 'ch341->tx_buf + 1', using 'len'
as the length is incorrect because:
It causes an out-of-bounds read from 'trans->tx_buf' (which has size
'trans->len', i.e., 'len - 1' in this context).
It can cause an out-of-bounds write to 'ch341->tx_buf' if 'len' is CH341_PACKET_LENGTH (32). Writing 32 bytes to ch341->tx_buf + 1 overflows the buffer.
Fix this by copying 'len - 1' bytes.
Wiz
CVE-2023-53867 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53867 CVE-2023-53867 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53867 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ceph: fix potential use-after-free bug when trimming caps
When trimming the caps and just after the 'session->s_cap_lock' is
released in ceph_iterate_session_caps() the cap maybe removed by
another thread, and when using the stale cap memory in the callbacks
it will trigger use-after-free crash.
We need to check the existence of the cap just after the 'ci->i_ceph_lock'
being acquired. And do nothing if it's already removed.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabi
Wiz
CVE-2025-68243 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68243 CVE-2025-68243 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68243 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFS: Check the TLS certificate fields in nfs_match_client()
If the TLS security policy is of type RPC_XPRTSEC_TLS_X509, then the
cert_serial and privkey_serial fields need to match as well since they
define the client's identity, as presented to the server.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-kvm
linux-aws
Sources
NVD
Debian 14 Has Fix Added at: Dec 1
Wiz
CVE-2025-68788 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68788 CVE-2025-68788 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68788 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fsnotify: do not generate ACCESS/MODIFY events on child for special files
inotify/fanotify do not allow users with no read access to a file to
subscribe to events (e.g. IN_ACCESS/IN_MODIFY), but they do allow the
same user to subscribe for watching events on children when the user
has access to the parent directory (e.g. /dev).
Users with no read access to a file but with read access to its parent
directory can still stat the file and see if it was accessed/modified
via atime/mtime change.
The same is not true for special files (e.g. /dev/null). Users will not
generally observe atime/mtime changes when other users read/write to
special files, only
Wiz
CVE-2023-54052 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54052 CVE-2023-54052 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54052 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7921: fix skb leak by txs missing in AMSDU
txs may be dropped if the frame is aggregated in AMSDU. When the problem
shows up, some SKBs would be hold in driver to cause network stopped
temporarily. Even if the problem can be recovered by txs timeout handling,
mt7921 still need to disable txs in AMSDU to avoid this issue.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libra
Wiz
CVE-2023-54191 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54191 CVE-2023-54191 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54191 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7996: fix memory leak in mt7996_mcu_exit
Always purge mcu skb queues in mt7996_mcu_exit routine even if
mt7996_firmware_state fails.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-devel
kernel-debug-uki-virt-addons
Sources
NVD
Red Hat 8 Severity MEDIUM Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity MEDIUM Has Fix Added at: Dec 31, 2025
Wiz
CVE-2026-23140 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23140 [MEDIUM] CVE-2026-23140 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23140 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf, test_run: Subtract size of xdp_frame from allowed metadata size
The xdp_frame structure takes up part of the XDP frame headroom,
limiting the size of the metadata. However, in bpf_test_run, we don't
take this into account, which makes it possible for userspace to supply
a metadata size that is too large (taking up the entire headroom).
If userspace supplies such a large metadata size in live packet mode,
the xdp_update_frame_from_buff() call in xdp_test_run_init_page() call
will fail, after which packet transmission proceeds with an
uninitialised frame structure, leading to the usual Bad Stuff.
The commit in the Fixes tag fixed a related bug
Wiz
CVE-2025-71086 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71086 [HIGH] CVE-2025-71086 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71086 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: rose: fix invalid array index in rose_kill_by_device()
rose_kill_by_device() collects sockets into a local array[] and then
iterates over them to disconnect sockets bound to a device being brought
down.
The loop mistakenly indexes array[cnt] instead of array[i]. For cnt <
ARRAY_SIZE(array), this reads an uninitialized entry; for cnt ==
ARRAY_SIZE(array), it is an out-of-bounds read. Either case can lead to
an invalid socket pointer dereference and also leaks references taken
via sock_hold().
Fix the index to use i.
Source : NVD
## 7.8
Score
Published January 13, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Li
Wiz
CVE-2023-53999 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53999 CVE-2023-53999 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53999 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: TC, Fix internal port memory leak
The flow rule can be splited, and the extra post_act rules are added
to post_act table. It's possible to trigger memleak when the rule
forwards packets from internal port and over tunnel, in the case that,
for example, CT 'new' state offload is allowed. As int_port object is
assigned to the flow attribute of post_act rule, and its refcnt is
incremented by mlx5e_tc_int_port_get(), but mlx5e_tc_int_port_put() is
not called, the refcnt is never decremented, then int_port is never
freed.
The kmemleak reports the following error:
unreferenced object 0xffff888128204b80 (size 64):
comm "handler20", pid 50121, j
Wiz
CVE-2026-23050 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23050 CVE-2026-23050 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23050 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pNFS: Fix a deadlock when returning a delegation during open()
Ben Coddington reports seeing a hang in the following stack trace:
0 [ffffd0b50e1774e0] __schedule at ffffffff9ca05415
1 [ffffd0b50e177548] schedule at ffffffff9ca05717
2 [ffffd0b50e177558] bit_wait at ffffffff9ca061e1
3 [ffffd0b50e177568] __wait_on_bit at ffffffff9ca05cfb
4 [ffffd0b50e1775c8] out_of_line_wait_on_bit at ffffffff9ca05ea5
5 [ffffd0b50e177618] pnfs_roc at ffffffffc154207b [nfsv4]
6 [ffffd0b50e1776b8] _nfs4_proc_delegreturn at ffffffffc1506586 [nfsv4]
7 [ffffd0b50e177788] nfs4_proc_delegreturn at ffffffffc1507480 [nfsv4]
8 [ffffd0b50e1777f8] nfs_do_return_delegation at fffff
Wiz
CVE-2026-23086 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23086 [MEDIUM] CVE-2026-23086 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23086 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vsock/virtio: cap TX credit to local buffer size
The virtio transports derives its TX credit directly from peer_buf_alloc,
which is set from the remote endpoint's SO_VM_SOCKETS_BUFFER_SIZE value.
On the host side this means that the amount of data we are willing to
queue for a connection is scaled by a guest-chosen buffer size, rather
than the host's own vsock configuration. A malicious guest can advertise
a large buffer and read slowly, causing the host to allocate a
correspondingly large amount of sk_buff memory.
The same thing would happen in the guest with a malicious host, since
virtio transports share the same code base.
Introduce a small he
Wiz
CVE-2025-71117 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71117 [MEDIUM] CVE-2025-71117 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71117 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: Remove queue freezing from several sysfs store callbacks
Freezing the request queue from inside sysfs store callbacks may cause a
deadlock in combination with the dm-multipath driver and the
queue_if_no_path option. Additionally, freezing the request queue slows
down system boot on systems where sysfs attributes are set synchronously.
Fix this by removing the blk_mq_freeze_queue() / blk_mq_unfreeze_queue()
calls from the store callbacks that do not strictly need these callbacks.
Add the __data_racy annotation to request_queue.rq_timeout to suppress
KCSAN data race reports about the rq_timeout reads.
This patch may cause a small delay in app
Wiz
CVE-2026-23458 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23458 CVE-2026-23458 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23458 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct()
ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the
netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the
conntrack reference immediately after netlink_dump_start(). When the
dump spans multiple rounds, the second recvmsg() triggers the dump
callback which dereferences the now-freed conntrack via nfct_help(ct),
leading to a use-after-free on ct->ext.
The bug is that the netlink_dump_control has no .start or .done
callbacks to manage the conntrack reference across dump rounds. Other
dump functions in the same file (e.g. ctnetlink_get_conntrack) proper
Wiz
CVE-2025-68747 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68747 CVE-2025-68747 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68747 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/panthor: Fix UAF on kernel BO VA nodes
If the MMU is down, panthor_vm_unmap_range() might return an error.
We expect the page table to be updated still, and if the MMU is blocked,
the rest of the GPU should be blocked too, so no risk of accessing
physical memory returned to the system (which the current code doesn't
cover for anyway).
Proceed with the rest of the cleanup instead of bailing out and leaving
the va_node inserted in the drm_mm, which leads to UAF when other
adjacent nodes are removed from the drm_mm tree.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit
Wiz
CVE-2026-23275 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23275 [HIGH] CVE-2026-23275 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23275 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring: ensure ctx->rings is stable for task work flags manipulation
If DEFER_TASKRUN | SETUP_TASKRUN is used and task work is added while
the ring is being resized, it's possible for the OR'ing of
IORING_SQ_TASKRUN to happen in the small window of swapping into the
new rings and the old rings being freed.
Prevent this by adding a 2nd ->rings pointer, ->rings_rcu, which is
protected by RCU. The task work flags manipulation is inside RCU
already, and if the resize ring freeing is done post an RCU synchronize,
then there's no need to add locking to the fast path of task work
additions.
Note: this is only done for DEFER_TASKRUN, as that's the only
Wiz
CVE-2023-54214 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54214 CVE-2023-54214 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54214 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: L2CAP: Fix potential user-after-free
This fixes all instances of which requires to allocate a buffer calling
alloc_skb which may release the chan lock and reacquire later which
makes it possible that the chan is disconnected in the meantime.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-macros
kernel-64k-debug-modules-extra
Sources
NVD
Debian 11, 12, 1
Wiz
CVE-2026-23249 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23249 CVE-2026-23249 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23249 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfs: check for deleted cursors when revalidating two btrees
The free space and inode btree repair functions will rebuild both btrees
at the same time, after which it needs to evaluate both btrees to
confirm that the corruptions are gone.
However, Jiaming Zhang ran syzbot and produced a crash in the second
xchk_allocbt call. His root-cause analysis is as follows (with minor
corrections):
In xrep_revalidate_allocbt(), xchk_allocbt() is called twice (first
for BNOBT, second for CNTBT). The cause of this issue is that the
first call nullified the cursor required by the second call.
Let's first enter xrep_revalidate_allocbt() via following call chain:
Wiz
CVE-2023-54129 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54129 CVE-2023-54129 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54129 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
octeontx2-af: Add validation for lmac type
Upon physical link change, firmware reports to the kernel about the
change along with the details like speed, lmac_type_id, etc.
Kernel derives lmac_type based on lmac_type_id received from firmware.
In a few scenarios, firmware returns an invalid lmac_type_id, which
is resulting in below kernel panic. This patch adds the missing
validation of the lmac_type_id field.
Internal error: Oops: 96000005 [#1] PREEMPT SMP
[ 35.321595] Modules linked in:
[ 35.328982] CPU: 0 PID: 31 Comm: kworker/0:1 Not tainted
5.4.210-g2e3169d8e1bc-dirty #17
[ 35.337014] Hardware name: Marvell CN103XX board (DT)
[ 35.344297] Work
Wiz
CVE-2025-68373 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68373 CVE-2025-68373 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68373 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md: avoid repeated calls to del_gendisk
There is a uaf problem which is found by case 23rdev-lifetime:
Oops: general protection fault, probably for non-canonical address 0xdead000000000122
RIP: 0010:bdi_unregister+0x4b/0x170
Call Trace: __del_gendisk+0x356/0x3e0
mddev_unlock+0x351/0x360
rdev_attr_store+0x217/0x280
kernfs_fop_write_iter+0x14a/0x210
vfs_write+0x29e/0x550
ksys_write+0x74/0xf0
do_syscall_64+0xbb/0x380
entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7ff5250a177e
The sequence is:
rdev remove path gets reconfig_mutex
rdev remove path release reconfig_mutex in mddev_unlock
md stop calls do_md_stop and sets MD_DELETED
rdev remove
Wiz
CVE-2022-50847 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50847 CVE-2022-50847 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50847 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/bridge: it6505: Initialize AUX channel in it6505_i2c_probe
During device boot, the HPD interrupt could be triggered before the DRM
subsystem registers it6505 as a DRM bridge. In such cases, the driver
tries to access AUX channel and causes NULL pointer dereference.
Initializing the AUX channel earlier to prevent such error.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
k
Wiz
CVE-2022-50882 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50882 CVE-2022-50882 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50882 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: uvcvideo: Fix memory leak in uvc_gpio_parse
Previously the unit buffer was allocated before checking the IRQ for
privacy GPIO. In case of error, the unit buffer was leaked.
Allocate the unit buffer after the IRQ to avoid it.
Addresses-Coverity-ID: 1474639 ("Resource leak")
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug
kernel-debug-uki-virt
Sources
Wiz
CVE-2026-23456 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23456 CVE-2026-23456 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23456 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case
In decode_int(), the CONS case calls get_bits(bs, 2) to read a length
value, then calls get_uint(bs, len) without checking that len bytes
remain in the buffer. The existing boundary check only validates the
2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint()
reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte
slab-out-of-bounds read.
Add a boundary check for len bytes after get_bits() and before
get_uint().
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Ex
Wiz
CVE-2026-23461 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23461 CVE-2026-23461 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23461 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user
After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in
hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to
conn->users. However, l2cap_register_user() and l2cap_unregister_user()
don't use conn->lock, creating a race condition where these functions can
access conn->users and conn->hchan concurrently with l2cap_conn_del().
This can lead to use-after-free and list corruption bugs, as reported
by syzbot.
Fix this by changing l2cap_register_user() and l2cap_unregister_user()
to use conn->lock instead of hci_dev_lock(), ensuring consistent locking
for the l2cap
Wiz
CVE-2026-23313 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23313 CVE-2026-23313 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23313 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i40e: Fix preempt count leak in napi poll tracepoint
Using get_cpu() in the tracepoint assignment causes an obvious preempt
count leak because nothing invokes put_cpu() to undo it:
softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101?
This clearly has seen a lot of testing in the last 3+ years...
Use smp_processor_id() instead.
Source : NVD
## 7.1
Score
Published March 25, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exp
Wiz
CVE-2023-54259 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54259 CVE-2023-54259 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54259 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
soundwire: bus: Fix unbalanced pm_runtime_put() causing usage count underflow
This reverts commit
443a98e649b4 ("soundwire: bus: use pm_runtime_resume_and_get()")
Change calls to pm_runtime_resume_and_get() back to pm_runtime_get_sync().
This fixes a usage count underrun caused by doing a pm_runtime_put() even
though pm_runtime_resume_and_get() returned an error.
The three affected functions ignore -EACCES error from trying to get
pm_runtime, and carry on, including a put at the end of the function.
But pm_runtime_resume_and_get() does not increment the usage count if it
returns an error. So in the -EACCES case you must not call
pm_runtime_put().
Wiz
CVE-2023-53993 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53993 CVE-2023-53993 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53993 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI/DOE: Fix memory leak with CONFIG_DEBUG_OBJECTS=y
After a pci_doe_task completes, its work_struct needs to be destroyed
to avoid a memory leak with CONFIG_DEBUG_OBJECTS=y.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
perf
bpftool
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Red Hat 9 Severity LOW Has Fix Added at:
Wiz
CVE-2023-54179 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54179 CVE-2023-54179 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54179 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Array index may go out of bound
Klocwork reports array 'vha->host_str' of size 16 may use index value(s)
16..19. Use snprintf() instead of sprintf().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64kb-devel
kernel-docs-html
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6, 7 Severity M
Wiz
CVE-2026-23327 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23327 CVE-2026-23327 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23327 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cxl/mbox: validate payload size before accessing contents in cxl_payload_from_user_allowed()
cxl_payload_from_user_allowed() casts and dereferences the input
payload without first verifying its size. When a raw mailbox command
is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG,
which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer,
triggering a KASAN splat:
BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683
Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258
CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (
Wiz
CVE-2022-50758 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50758 CVE-2022-50758 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50758 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: vt6655: fix potential memory leak
In function device_init_td0_ring, memory is allocated for member
td_info of priv->apTD0Rings[i], with i increasing from 0. In case of
allocation failure, the memory is freed in reversed order, with i
decreasing to 0. However, the case i=0 is left out and thus memory is
leaked.
Modify the memory freeing loop to include the case i=0.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probabili
Wiz
CVE-2026-23214 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23214 [MEDIUM] CVE-2026-23214 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23214 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: reject new transactions if the fs is fully read-only
[BUG]
There is a bug report where a heavily fuzzed fs is mounted with all
rescue mount options, which leads to the following warnings during
unmount:
BTRFS: Transaction aborted (error -22)
Modules linked in:
CPU: 0 UID: 0 PID: 9758 Comm: repro.out Not tainted
6.19.0-rc5-00002-gb71e635feefc #7 PREEMPT(full)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:find_free_extent_update_loop fs/btrfs/extent-tree.c:4208 [inline]
RIP: 0010:find_free_extent+0x52f0/0x5d20 fs/btrfs/extent-tree.c:4611
Call Trace: btrfs_reserve_extent+0x2cd/0x790 fs/btrfs/extent-tr
Wiz
CVE-2023-54144 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54144 CVE-2023-54144 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54144 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amdkfd: Fix kernel warning during topology setup
This patch fixes the following kernel warning seen during
driver load by correctly initializing the p2plink attr before
creating the sysfs file:
[ +0.002865] ------------[ cut here ]------------
[ +0.002327] kobject: '(null)' (0000000056260cfb): is not initialized, yet kobject_put() is being called.
[ +0.004780] WARNING: CPU: 32 PID: 1006 at lib/kobject.c:718 kobject_put+0xaa/0x1c0
[ +0.001361] Call Trace:
[ +0.001234] [ +0.001067] kfd_remove_sysfs_node_entry+0x24a/0x2d0 [amdgpu]
[ +0.003147] kfd_topology_update_sysfs+0x3d/0x750 [amdgpu]
[ +0.002890] kfd_topology_add_device+0xbd7/0xc70 [amdgpu]
[
Wiz
CVE-2026-23316 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23316 CVE-2026-23316 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23316 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ipv4: fix ARM64 alignment fault in multipath hash seed
struct sysctl_fib_multipath_hash_seed
fib_multipath_hash_from_keys()
READ_ONCE()
mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;
While this silently works on GCC by falling back to unaligned regular
loads which the ARM64 kernel tolerates, it causes a fatal kernel panic
when compiled with Clang and LTO enabled.
READ_ONCE()
ldar
ldapr
ldar
ldar
READ_ONCE()
u32
ldar Wn
WRITE_ONCE()
proc_fib_multipath_hash_set_seed()
str
WRITE_ONCE()
READ_ONCE()
user_seed
proc_fib_multipath_hash_seed()
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Tec
Wiz
CVE-2023-54132 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54132 CVE-2023-54132 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54132 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: stop parsing non-compact HEAD index if clusterofs is invalid
Syzbot generated a crafted image [1] with a non-compact HEAD index of
clusterofs 33024 while valid numbers should be 0 ~ lclustersize-1,
which causes the following unexpected behavior as below:
BUG: unable to handle page fault for address: fffff52101a3fff9
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 23ffed067 P4D 23ffed067 PUD 0
Oops: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 4398 Comm: kworker/u5:1 Not tainted 6.3.0-rc6-syzkaller-g09a9639e56c0 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023
Wo
Wiz
CVE-2025-68367 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68367 CVE-2025-68367 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68367 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
macintosh/mac_hid: fix race condition in mac_hid_toggle_emumouse
The following warning appears when running syzkaller, and this issue also
exists in the mainline code.
------------[ cut here ]------------
list_add double add: new=ffffffffa57eee28, prev=ffffffffa57eee28, next=ffffffffa5e63100.
WARNING: CPU: 0 PID: 1491 at lib/list_debug.c:35 __list_add_valid_or_report+0xf7/0x130
Modules linked in:
CPU: 0 PID: 1491 Comm: syz.1.28 Not tainted 6.6.0+ #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:__list_add_valid_or_report+0xf7/0x130
RSP: 0018:ff1100010dfb7b78 EFLAGS: 000
Wiz
CVE-2025-71110 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71110 [HIGH] CVE-2025-71110 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71110 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/slub: reset KASAN tag in defer_free() before accessing freed memory
When CONFIG_SLUB_TINY is enabled, kfree_nolock() calls kasan_slab_free()
before defer_free(). On ARM64 with MTE (Memory Tagging Extension),
kasan_slab_free() poisons the memory and changes the tag from the
original (e.g., 0xf3) to a poison tag (0xfe).
When defer_free() then tries to write to the freed object to build the
deferred free list via llist_add(), the pointer still has the old tag,
causing a tag mismatch and triggering a KASAN use-after-free report:
BUG: KASAN: slab-use-after-free in defer_free+0x3c/0xbc mm/slub.c:6537
Write at addr f3f000000854f020 by task kworker/u8:
Wiz
CVE-2026-23202 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23202 [MEDIUM] CVE-2026-23202 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23202 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: tegra210-quad: Protect curr_xfer in tegra_qspi_combined_seq_xfer
The curr_xfer field is read by the IRQ handler without holding the lock
to check if a transfer is in progress. When clearing curr_xfer in the
combined sequence transfer loop, protect it with the spinlock to prevent
a race with the interrupt handler.
Protect the curr_xfer clearing at the exit path of
tegra_qspi_combined_seq_xfer() with the spinlock to prevent a race
with the interrupt handler that reads this field.
Without this protection, the IRQ handler could read a partially updated
curr_xfer value, leading to NULL pointer dereference or use-after-free.
Source : NVD
## 5.5
Wiz
CVE-2023-54097 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54097 CVE-2023-54097 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54097 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regulator: stm32-pwr: fix of_iomap leak
Smatch reports:
drivers/regulator/stm32-pwr.c:166 stm32_pwr_regulator_probe() warn:
'base' from of_iomap() not released on lines: 151,166.
In stm32_pwr_regulator_probe(), base is not released
when devm_kzalloc() fails to allocate memory or
devm_regulator_register() fails to register a new regulator device,
which may cause a leak.
To fix this issue, replace of_iomap() with
devm_platform_ioremap_resource(). devm_platform_ioremap_resource()
is a specialized function for platform devices.
It allows 'base' to be automatically released whether the probe
function succeeds or fails.
Besides, use IS_ERR(base) instea
Wiz
CVE-2025-71091 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71091 [HIGH] CVE-2025-71091 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71091 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
team: fix check for port enabled in team_queue_override_port_prio_changed()
There has been a syzkaller bug reported recently with the following
trace:
list_del corruption, ffff888058bea080->prev is LIST_POISON2 (dead000000000122)
------------[ cut here ]------------
kernel BUG at lib/list_debug.c:59!
Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
CPU: 3 UID: 0 PID: 21246 Comm: syz.0.2928 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:__list_del_entry_valid_or_report+0x13e/0x200 lib/list_debug.c:59
Code: 48 c7 c7 e0 71 f0 8b e8 30 08 ef fc 90 0f 0b
Wiz
CVE-2023-54160 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54160 CVE-2023-54160 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54160 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
firmware: arm_sdei: Fix sleep from invalid context BUG
Running a preempt-rt (v6.2-rc3-rt1) based kernel on an Ampere Altra
triggers:
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 24, name: cpuhp/0
preempt_count: 0, expected: 0
RCU nest depth: 0, expected: 0
3 locks held by cpuhp/0/24:
#0: ffffda30217c70d0 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248
#1: ffffda30217c7120 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248
#2: ffffda3021c711f0 (sdei_list_lock){....}-{3:3}, at: sdei_cpuhp_up+0x3c/0x130
irq event stamp: 36
hardi
Wiz
CVE-2022-50833 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50833 CVE-2022-50833 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50833 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: use hdev->workqueue when queuing hdev->{cmd,ncmd}_timer works
syzbot is reporting attempt to schedule hdev->cmd_work work from system_wq
WQ into hdev->workqueue WQ which is under draining operation [1], for
commit c8efcc2589464ac7 ("workqueue: allow chained queueing during
destruction") does not allow such operation.
The check introduced by commit 877afadad2dce8aa ("Bluetooth: When HCI work
queue is drained, only queue chained work") was incomplete.
Use hdev->workqueue WQ when queuing hdev->{cmd,ncmd} timer works because
hci {cmd,ncmd}_timeout() calls queue_work(hdev->workqueue). Also, protect
the queuing operation with RCU read lock in
Wiz
CVE-2022-50832 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50832 CVE-2022-50832 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50832 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: wilc1000: fix potential memory leak in wilc_mac_xmit()
The wilc_mac_xmit() returns NETDEV_TX_OK without freeing skb, add
dev_kfree_skb() to fix it. Compile tested only.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-iot
kernel-modules-core
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity
Wiz
CVE-2025-71094 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71094 [MEDIUM] CVE-2025-71094 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71094 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: asix: validate PHY address before use
The ASIX driver reads the PHY address from the USB device via
asix_read_phy_addr(). A malicious or faulty device can return an
invalid address (>= PHY_MAX_ADDR), which causes a warning in
mdiobus_get_phy():
addr 207 out of range
WARNING: drivers/net/phy/mdio_bus.c:76
Validate the PHY address in asix_read_phy_addr() and remove the
now-redundant check in ax88172a.c.
Source : NVD
## 5.5
Score
Published January 13, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Wiz
CVE-2022-50774 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50774 CVE-2022-50774 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50774 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: qat - fix DMA transfer direction
When CONFIG_DMA_API_DEBUG is selected, while running the crypto self
test on the QAT crypto algorithms, the function add_dma_entry() reports
a warning similar to the one below, saying that overlapping mappings
are not supported. This occurs in tests where the input and the output
scatter list point to the same buffers (i.e. two different scatter lists
which point to the same chunks of memory).
The logic that implements the mapping uses the flag DMA_BIDIRECTIONAL
for both the input and the output scatter lists which leads to
overlapped write mappings. These are not supported by the DMA layer.
Fix by specifyi
Wiz
CVE-2025-68355 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68355 CVE-2025-68355 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68355 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix exclusive map memory leak
When excl_prog_hash is 0 and excl_prog_hash_size is non-zero, the map also
needs to be freed. Otherwise, the map memory will not be reclaimed, just
like the memory leak problem reported by syzbot [1].
syzbot reported:
BUG: memory leak
backtrace (crc 7b9fb9b4):
map_create+0x322/0x11e0 kernel/bpf/syscall.c:1512
__sys_bpf+0x3556/0x3610 kernel/bpf/syscall.c:6131
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Proba
Wiz
CVE-2026-23241 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23241 CVE-2026-23241 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23241 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
audit: add missing syscalls to read class
The "at" variant of getxattr() and listxattr() are missing from the
audit read class. Calling getxattrat() or listxattrat() on a file to
read its extended attributes will bypass audit rules such as:
-w /tmp/test -p rwa -k test_rwa
The current patch adds missing syscalls to the audit read class.
Source : NVD
## 5.1
Score
Published March 17, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probability (EPSS
Wiz
CVE-2023-54269 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54269 CVE-2023-54269 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54269 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
SUNRPC: double free xprt_ctxt while still in use
When an RPC request is deferred, the rq_xprt_ctxt pointer is moved out
of the svc_rqst into the svc_deferred_req.
When the deferred request is revisited, the pointer is copied into
the new svc_rqst - and also remains in the svc_deferred_req.
In the (rare?) case that the request is deferred a second time, the old
svc_deferred_req is reused - it still has all the correct content.
However in that case the rq_xprt_ctxt pointer is NOT cleared so that
when xpo_release_xprt is called, the ctxt is freed (UDP) or possible
added to a free list (RDMA).
When the deferred request is revisited for a second time, i
Wiz
CVE-2026-23126 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23126 [MEDIUM] CVE-2026-23126 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23126 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netdevsim: fix a race issue related to the operation on bpf_bound_progs list
The netdevsim driver lacks a protection mechanism for operations on the
bpf_bound_progs list. When the nsim_bpf_create_prog() performs
list_add_tail, it is possible that nsim_bpf_destroy_prog() is
simultaneously performs list_del. Concurrent operations on the list may
lead to list corruption and trigger a kernel crash as follows:
[ 417.290971] kernel BUG at lib/list_debug.c:62!
[ 417.290983] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 417.290992] CPU: 10 PID: 168 Comm: kworker/10:1 Kdump: loaded Not tainted 6.19.0-rc5 #1
[ 417.291003] Hardware name: QEMU Standard PC (Q35
Wiz
CVE-2025-68811 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68811 CVE-2025-68811 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68811 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
svcrdma: use rc_pageoff for memcpy byte offset
svc_rdma_copy_inline_range added rc_curpage (page index) to the page
base instead of the byte offset rc_pageoff. Use rc_pageoff so copies
land within the current page.
Found by ZeroPath ( https://zeropath.com )
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Rocky Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek64k-modules
kernel-uek-doc
Sources
NVD
AlmaLinux 9 Severity
Wiz
CVE-2026-23026 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23026 [MEDIUM] CVE-2026-23026 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23026 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: qcom: gpi: Fix memory leak in gpi_peripheral_config()
Fix a memory leak in gpi_peripheral_config() where the original memory
pointed to by gchan->config could be lost if krealloc() fails.
The issue occurs when:
gchan->config points to previously allocated memory
krealloc() fails and returns NULL
The function directly assigns NULL to gchan->config, losing the reference to the original memory
The original memory becomes unreachable and cannot be freed
Fix this by using a temporary variable to hold the krealloc() result
and only updating gchan->config when the allocation succeeds.
Found via static analysis and code review.
Source : N
Wiz
CVE-2026-31407 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31407 CVE-2026-31407 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31407 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: conntrack: add missing netlink policy validations
Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink.
These attributes are used by the kernel without any validation.
Extend the netlink policies accordingly.
Quoting the reporter:
nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE
value directly to ct->proto.sctp.state without checking that it is
within the valid range. [..]
and: ... with exp->dir = 100, the access at
ct->master->tuplehash[100] reads 5600 bytes past the start of a
320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by
UBSAN.
Source : NVD
## 7.1
Score
Published April 6,
Wiz
CVE-2026-23200 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23200 [MEDIUM] CVE-2026-23200 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23200 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: Fix ECMP sibling count mismatch when clearing RTF_ADDRCONF
syzbot reported a kernel BUG in fib6_add_rt2node() when adding an IPv6
route. 0
Commit f72514b3c569 ("ipv6: clear RA flags when adding a static
route") introduced logic to clear RTF_ADDRCONF from existing routes
when a static route with the same nexthop is added. However, this
causes a problem when the existing route has a gateway.
When RTF_ADDRCONF is cleared from a route that has a gateway, that
route becomes eligible for ECMP, i.e. rt6_qualify_for_ecmp() returns
true. The issue is that this route was never added to the
fib6_siblings list.
This leads to a mismatch between the foll
Wiz
CVE-2025-68765 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68765 CVE-2025-68765 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68765 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mt76: mt7615: Fix memory leak in mt7615_mcu_wtbl_sta_add()
In mt7615_mcu_wtbl_sta_add(), an skb sskb is allocated. If the
subsequent call to mt76_connac_mcu_alloc_wtbl_req() fails, the function
returns an error without freeing sskb, leading to a memory leak.
Fix this by calling dev_kfree_skb() on sskb in the error handling path
to ensure it is properly released.
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Wiz
CVE-2023-54133 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54133 CVE-2023-54133 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54133 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfp: clean mc addresses in application firmware when closing port
When moving devices from one namespace to another, mc addresses are
cleaned in software while not removed from application firmware. Thus
the mc addresses are remained and will cause resource leak.
__dev_mc_unsync
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-allwinner
dtb-exynos
Sources
NVD
Debian 13
Wiz
CVE-2023-53837 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53837 CVE-2023-53837 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53837 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm: fix NULL-deref on snapshot tear down
In case of early initialisation errors and on platforms that do not use
the DPU controller, the deinitilisation code can be called with the kms
pointer set to NULL.
Patchwork: https://patchwork.freedesktop.org/patch/525099/
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-default-base
linux-azure-5.15
Sources
NVD
Debian 1
Wiz
CVE-2026-23311 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23311 CVE-2026-23311 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23311 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/core: Fix invalid wait context in ctx_sched_in()
Lockdep found a bug in the event scheduling when a pinned event was
failed and wakes up the threads in the ring buffer like below.
It seems it should not grab a wait-queue lock under perf-context lock.
Let's do it with irq_work.
[ 39.913691] =============================
[ 39.914157] [ BUG: Invalid wait context ]
[ 39.914623] 6.15.0-next-20250530-next-2025053 #1 Not tainted
[ 39.915271] -----------------------------
[ 39.915731] repro/837 is trying to lock:
[ 39.916191] ffff88801acfabd8 (&event->waitq){....}-{3:3}, at: __wake_up+0x26/0x60
[ 39.917182] other info that might help us debug this:
[
Wiz
CVE-2026-23379 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23379 CVE-2026-23379 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23379 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: ets: fix divide by zero in the offload path
Offloading ETS requires computing each class' WRR weight: this is done by
averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned
int, the same integer size as the individual DRR quanta, can overflow and
even cause division by zero, like it happened in the following splat:
Oops: divide error: 0000 [#1] SMP PTI
CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full)
Tainted: [E]=UNSIGNED_MODULE
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87
Wiz
CVE-2023-54017 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54017 CVE-2023-54017 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54017 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/pseries: fix possible memory leak in ibmebus_bus_init()
If device_register() returns error in ibmebus_bus_init(), name of kobject
which is allocated in dev_set_name() called in device_add() is leaked.
As comment of device_add() says, it should call put_device() to drop
the reference count that was set in device_initialize() when it fails,
so the name can be freed in kobject_cleanup().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exp
Wiz
CVE-2026-23170 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23170 [MEDIUM] CVE-2026-23170 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23170 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/imx/tve: fix probe device leak
Make sure to drop the reference taken to the DDC device during probe on
probe failure (e.g. probe deferral) and on driver unbind.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-oracle
linux-kvm
Sources
NVD
Debian 11, 12, 13, 14 Severity MEDIUM Has Fix Added at: Feb 15, 2026
Echo Severity MEDIUM Ha
Wiz
CVE-2023-54159 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54159 CVE-2023-54159 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54159 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: mtu3: fix kernel panic at qmu transfer done irq handler
When handle qmu transfer irq, it will unlock @mtu->lock before give back
request, if another thread handle disconnect event at the same time, and
try to disable ep, it may lock @mtu->lock and free qmu ring, then qmu
irq hanlder may get a NULL gpd, avoid the KE by checking gpd's value before
handling it.
e.g.
qmu done irq on cpu0 thread running on cpu1
qmu_done_tx()
handle gpd [0]
mtu3_requ_complete() mtu3_gadget_ep_disable()
unlock @mtu->lock
give back request lock @mtu->lock
mtu3_ep_disable()
mtu3_gpd_ring_free()
unlock @mtu->lock
lock @mtu->lock
get next gpd 1
Source : NVD
Published
Wiz
CVE-2026-23117 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23117 [MEDIUM] CVE-2026-23117 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23117 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: add missing ice_deinit_hw() in devlink reinit path
devlink-reload results in ice_init_hw failed error, and then removing
the ice driver causes a NULL pointer dereference.
[ +0.102213] ice 0000:ca:00.0: ice_init_hw failed: -16
...
[ +0.000001] Call Trace:
[ +0.000003] [ +0.000006] ice_unload+0x8f/0x100 [ice]
[ +0.000081] ice_remove+0xba/0x300 [ice]
Commit 1390b8b3d2be ("ice: remove duplicate call to ice_deinit_hw() on
error paths") removed ice_deinit_hw() from ice_deinit_dev(). As a result
ice_devlink_reinit_down() no longer calls ice_deinit_hw(), but
ice_devlink_reinit_up() still calls ice_init_hw(). Since the control
queues are not uninitial
Wiz
CVE-2026-23430 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23430 CVE-2026-23430 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23430 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/vmwgfx: Don't overwrite KMS surface dirty tracker
We were overwriting the surface's dirty tracker here causing a memory leak.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-modules-partner
kernel-debug-modules-internal
Sources
NVD
Debian 14 Has Fix Added at: Apr 05, 2026
Red Hat 6, 9, 10 Severity LOW No Fix Added at: Apr 05, 2026
Ubuntu 16.04, 18.04, 20.0
Wiz
CVE-2025-68333 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68333 [MEDIUM] CVE-2025-68333 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68333 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sched_ext: Fix possible deadlock in the deferred_irq_workfn()
For PREEMPT_RT=y kernels, the deferred_irq_workfn() is executed in
the per-cpu irq_work/* task context and not disable-irq, if the rq
returned by container_of() is current CPU's rq, the following scenarios
may occur:
lock(&rq->__lock); lock(&rq->__lock);
This commit use IRQ_WORK_INIT_HARD() to replace init_irq_work() to
initialize rq->scx.deferred_irq_work, make the deferred_irq_workfn()
is always invoked in hard-irq context.
Source : NVD
## 5.5
Score
Published December 22, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit
Wiz
CVE-2023-53858 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53858 CVE-2023-53858 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53858 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() in case of error
If clk_get_rate() fails, the clk that has just been allocated needs to be
freed.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-amd
kernel-default-base-rebuild
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 09, 2025
Echo Has Fix Added at: Dec 09, 2025
Red Hat 9 Severity
Wiz
CVE-2025-68283 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68283 CVE-2025-68283 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68283 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: replace BUG_ON with bounds check for map->max_osd
OSD indexes come from untrusted network packets. Boundary checks are
added to validate these against map->max_osd.
[ idryomov: drop BUG_ON in ceph_get_primary_affinity(), minor cosmetic
edits ]
Source : NVD
## 7.1
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 11.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-selftests-internal
linux-azure-6.17
Wiz
CVE-2025-71130 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71130 [MEDIUM] CVE-2025-71130 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71130 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915/gem: Zero-initialize the eb.vma array in i915_gem_do_execbuffer
Initialize the eb.vma array with values of 0 when the eb structure is
first set up. In particular, this sets the eb->vma[i].vma pointers to
NULL, simplifying cleanup and getting rid of the bug described below.
During the execution of eb_lookup_vmas(), the eb->vma array is
successively filled up with struct eb_vma objects. This process includes
calling eb_add_vma(), which might fail; however, even in the event of
failure, eb->vma[i].vma is set for the currently processed buffer.
If eb_add_vma() fails, eb_lookup_vmas() returns with an error, which
prompts a call to eb_release_v
Wiz
CVE-2023-54070 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54070 CVE-2023-54070 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54070 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
igb: clean up in all error paths when enabling SR-IOV
After commit 50f303496d92 ("igb: Enable SR-IOV after reinit"), removing
the igb module could hang or crash (depending on the machine) when the
module has been loaded with the max_vfs parameter set to some value != 0.
In case of one test machine with a dual port 82580, this hang occurred:
[ 232.480687] igb 0000:41:00.1: removed PHC on enp65s0f1
[ 233.093257] igb 0000:41:00.1: IOV Disabled
[ 233.329969] pcieport 0000:40:01.0: AER: Multiple Uncorrected (Non-Fatal) err0
[ 233.340302] igb 0000:41:00.0: PCIe Bus Error: severity=Uncorrected (Non-Fata)
[ 233.352248] igb 0000:41:00.0: device [8086:1516]
Wiz
CVE-2023-54292 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54292 CVE-2023-54292 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54292 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/irdma: Fix data race on CQP request done
KCSAN detects a data race on cqp_request->request_done memory location
which is accessed locklessly in irdma_handle_cqp_op while being
updated in irdma_cqp_ce_handler.
Annotate lockless intent with READ_ONCE/WRITE_ONCE to avoid any
compiler optimizations like load fusing and/or KCSAN warning.
[222808.417128] BUG: KCSAN: data-race in irdma_cqp_ce_handler [irdma] / irdma_wait_event [irdma]
[222808.417532] write to 0xffff8e44107019dc of 1 bytes by task 29658 on cpu 5:
[222808.417610] irdma_cqp_ce_handler+0x21e/0x270 [irdma]
[222808.417725] cqp_compl_worker+0x1b/0x20 [irdma]
[222808.417827] process_one_wo
Wiz
CVE-2025-68348 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68348 CVE-2025-68348 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68348 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: fix memory leak in __blkdev_issue_zero_pages
Move the fatal signal check before bio_alloc() to prevent a memory
leak when BLKDEV_ZERO_KILLABLE is set and a fatal signal is pending.
Previously, the bio was allocated before checking for a fatal signal.
If a signal was pending, the code would break out of the loop without
freeing or chaining the just-allocated bio, causing a memory leak.
This matches the pattern already used in __blkdev_issue_write_zeroes()
where the signal check precedes the allocation.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA
Wiz
CVE-2022-50846 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50846 CVE-2022-50846 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50846 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: via-sdmmc: fix return value check of mmc_add_host()
mmc_add_host() may return error, if we ignore its return value,
it will lead two issues:
The memory that allocated in mmc_alloc_host() is leaked.
In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del().
Fix this by checking the return value and goto error path which
will call mmc_free_host().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV
Wiz
CVE-2023-54171 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54171 CVE-2023-54171 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54171 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tracing: Fix memory leak of iter->temp when reading trace_pipe
kmemleak reports:
unreferenced object 0xffff88814d14e200 (size 256):
comm "cat", pid 336, jiffies 4294871818 (age 779.490s)
hex dump (first 32 bytes):
04 00 01 03 00 00 00 00 08 00 00 00 00 00 00 00 ................
0c d8 c8 9b ff ff ff ff 04 5a ca 9b ff ff ff ff .........Z......
backtrace:
[ ] __kmalloc+0x4f/0x140
[ ] trace_find_next_entry+0xbb/0x1d0
[ ] trace_print_lat_context+0xaf/0x4e0
[ ] print_trace_line+0x3e0/0x950
[ ] tracing_read_pipe+0x2d9/0x5a0
[ ] vfs_read+0x143/0x520
[ ] ksys_read+0xbd/0x160
[ ] do_syscall_64+0x3f/0x90
[ ] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
when readi
Wiz
CVE-2026-23365 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23365 CVE-2026-23365 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23365 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: kalmia: validate USB endpoints
The kalmia driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it. If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2026-23018 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23018 [MEDIUM] CVE-2026-23018 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23018 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: release path before initializing extent tree in btrfs_read_locked_inode()
In btrfs_read_locked_inode() we are calling btrfs_init_file_extent_tree()
while holding a path with a read locked leaf from a subvolume tree, and
btrfs_init_file_extent_tree() may do a GFP_KERNEL allocation, which can
trigger reclaim.
This can create a circular lock dependency which lockdep warns about with
the following splat:
[6.1433] ======================================================
[6.1574] WARNING: possible circular locking dependency detected
[6.1583] 6.18.0+ #4 Tainted: G U
[6.1591] ------------------------------------------------------
[6.1599] kswapd0/11
Wiz
CVE-2022-50879 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50879 CVE-2022-50879 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50879 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
objtool: Fix SEGFAULT
find_insn() will return NULL in case of failure. Check insn in order
to avoid a kernel Oops for NULL pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-ipaclones-internal
kernel-modules
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW Has Fix Added a
Wiz
CVE-2025-68224 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68224 CVE-2025-68224 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68224 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
## 7.1
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-devel
kernel-zfcpdump-core
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 17, 2025
Echo Has Fix Added at: Dec 17, 2025
Red Hat 6, 7, 8, 9, 10 Severity LOW No Fix Added at: Dec 17, 2025
Ubuntu 16.04, 18.04, 20.04, 22.04, 24.04, 25.10 Severity MEDIUM No
Wiz
CVE-2022-50883 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50883 CVE-2022-50883 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50883 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Prevent decl_tag from being referenced in func_proto arg
Syzkaller managed to hit another decl_tag issue:
btf_func_proto_check kernel/bpf/btf.c:4506 [inline]
btf_check_all_types kernel/bpf/btf.c:4734 [inline]
btf_parse_type_sec+0x1175/0x1980 kernel/bpf/btf.c:4763
btf_parse kernel/bpf/btf.c:5042 [inline]
btf_new_fd+0x65a/0xb00 kernel/bpf/btf.c:6709
bpf_btf_load+0x6f/0x90 kernel/bpf/syscall.c:4342
__sys_bpf+0x50a/0x6c0 kernel/bpf/syscall.c:5034
__do_sys_bpf kernel/bpf/syscall.c:5093 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5091 [inline]
__x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5091
do_syscall_64+0x54/0x70 arch/x86/entry/common.c:48
This s
Wiz
CVE-2023-54143 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54143 CVE-2023-54143 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54143 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: mediatek: vcodec: fix resource leaks in vdec_msg_queue_init()
If we encounter any error in the vdec_msg_queue_init() then we need
to set "msg_queue->wdma_addr.size = 0;". Normally, this is done
inside the vdec_msg_queue_deinit() function. However, if the
first call to allocate &msg_queue->wdma_addr fails, then the
vdec_msg_queue_deinit() function is a no-op. For that situation, just
set the size to zero explicitly and return.
There were two other error paths which did not clean up before returning.
Change those error paths to goto mem_alloc_err.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
L
Wiz
CVE-2026-23128 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23128 [MEDIUM] CVE-2026-23128 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23128 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: Set __nocfi on swsusp_arch_resume()
A DABT is reported[1] on an android based system when resume from hiberate.
This happens because swsusp_arch_suspend_exit() is marked with SYM_CODE_*()
and does not have a CFI hash, but swsusp_arch_resume() will attempt to
verify the CFI hash when calling a copy of swsusp_arch_suspend_exit().
Given that there's an existing requirement that the entrypoint to
swsusp_arch_suspend_exit() is the first byte of the .hibernate_exit.text
section, we cannot fix this by marking swsusp_arch_suspend_exit() with
SYM_FUNC_*(). The simplest fix for now is to disable the CFI check in
swsusp_arch_resume().
Mark swsusp_arch
Wiz
CVE-2025-68191 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68191 CVE-2025-68191 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68191 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udp_tunnel: use netdev_warn() instead of netdev_WARN()
netdev_WARN() uses WARN/WARN_ON to print a backtrace along with
file and line information. In this case, udp_tunnel_nic_register()
returning an error is just a failed operation, not a kernel bug.
udp_tunnel_nic_register() can fail due to a memory allocation
failure (kzalloc() or udp_tunnel_nic_alloc()).
This is a normal runtime error and not a kernel bug.
Replace netdev_WARN() with netdev_warn() accordingly.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CIS
Wiz
CVE-2020-37011 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.4
CVE-2020-37011 [HIGH] CVE-2020-37011 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2020-37011 :
Linux Ubuntu vulnerability analysis and mitigation
Gnome Fonts Viewer 3.34.0 contains a heap corruption vulnerability that allows attackers to trigger an out-of-bounds write by crafting a malicious TTF font file. Attackers can generate a specially crafted TTF file with an oversized pattern to cause an infinite malloc() loop and potentially crash the gnome-font-viewer process.
Source : NVD
## 8.4
Score
Published January 29, 2026
Severity HIGH
CNA Score 8.4
Affected Technologies
Linux Ubuntu
Linux Red Hat
Has Public Exploit Yes
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 12.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
gnome-font-viewer
Sources
NVD
Echo S
Wiz
CVE-2026-23197 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23197 [MEDIUM] CVE-2026-23197 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23197 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i2c: imx: preserve error state in block data length handler
When a block read returns an invalid length, zero or >I2C_SMBUS_BLOCK_MAX,
the length handler sets the state to IMX_I2C_STATE_FAILED. However,
i2c_imx_master_isr() unconditionally overwrites this with
IMX_I2C_STATE_READ_CONTINUE, causing an endless read loop that overruns
buffers and crashes the system.
Guard the state transition to preserve error states set by the length
handler.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Dat
Wiz
CVE-2025-40353 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40353 CVE-2025-40353 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40353 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: mte: Do not warn if the page is already tagged in copy_highpage()
The arm64 copy_highpage() assumes that the destination page is newly
allocated and not MTE-tagged (PG_mte_tagged unset) and warns
accordingly. However, following commit 060913999d7a ("mm: migrate:
support poisoned recover from migrate folio"), folio_mc_copy() is called
before __folio_migrate_mapping(). If the latter fails (-EAGAIN), the
copy will be done again to the same destination page. Since
copy_highpage() already set the PG_mte_tagged flag, this second copy
will warn.
Replace the WARN_ON_ONCE(page already tagged) in the arm64
copy_highpage() with a comment.
Source : NVD
Wiz
CVE-2026-22982 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22982 [MEDIUM] CVE-2026-22982 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22982 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: mscc: ocelot: Fix crash when adding interface under a lag
Commit 15faa1f67ab4 ("lan966x: Fix crash when adding interface under a lag")
fixed a similar issue in the lan966x driver caused by a NULL pointer dereference.
The ocelot_set_aggr_pgids() function in the ocelot driver has similar logic
and is susceptible to the same crash.
This issue specifically affects the ocelot_vsc7514.c frontend, which leaves
unused ports as NULL pointers. The felix_vsc9959.c frontend is unaffected as
it uses the DSA framework which registers all ports.
Fix this by checking if the port pointer is valid before accessing it.
Source : NVD
## 5.5
Score
Published
Wiz
CVE-2022-50870 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50870 CVE-2022-50870 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50870 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/rtas: avoid device tree lookups in rtas_os_term()
rtas_os_term() is called during panic. Its behavior depends on a couple
of conditions in the /rtas node of the device tree, the traversal of
which entails locking and local IRQ state changes. If the kernel panics
while devtree_lock is held, rtas_os_term() as currently written could
hang.
Instead of discovering the relevant characteristics at panic time,
cache them in file-static variables at boot. Note the lookup for
"ibm,extended-os-term" is converted to of_property_read_bool() since it
is a boolean property, not an RTAS function token.
[mpe: Incorporate suggested change from Nick]
Source
Wiz
CVE-2023-53989 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53989 CVE-2023-53989 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53989 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: mm: fix VA-range sanity check
Both create_mapping_noalloc() and update_mapping_prot() sanity-check
their 'virt' parameter, but the check itself doesn't make much sense.
The condition used today appears to be a historical accident.
The sanity-check condition:
if ((virt >= PAGE_END) && (virt = VA_START) && (virt = PAGE_END) && (virt < VMALLOC_START)) {
[ ... warning here ... ]
return;
}
Correct the condition to check against the start of the TTBR1 address
space, which is currently PAGE_OFFSET. This simplifies the logic, and
more clearly matches the "outside kernel range" message in the warning.
Source : NVD
Published December 24, 2025
CNA
Wiz
CVE-2026-23112 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 9.8
CVE-2026-23112 [CRITICAL] CVE-2026-23112 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23112 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet-tcp: add bounds checks in nvmet_tcp_build_pdu_iovec
nvmet_tcp_build_pdu_iovec() could walk past cmd->req.sg when a PDU
length or offset exceeds sg_cnt and then use bogus sg->length/offset
values, leading to _copy_to_iter() GPF/KASAN. Guard sg_idx, remaining
entries, and sg->length/offset before building the bvec.
Source : NVD
## 9.8
Score
Published February 13, 2026
Severity CRITICAL
CNA Score 9.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 20.9
Exploitation Probability (EPSS) 0.1
Affecte
Wiz
CVE-2025-71134 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71134 [MEDIUM] CVE-2025-71134 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71134 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/page_alloc: change all pageblocks migrate type on coalescing
When a page is freed it coalesces with a buddy into a higher order page
while possible. When the buddy page migrate type differs, it is expected
to be updated to match the one of the page being freed.
However, only the first pageblock of the buddy page is updated, while the
rest of the pageblocks are left unchanged.
That causes warnings in later expand() and other code paths (like below),
since an inconsistency between migration type of the list containing the
page and the page-owned pageblocks migration types is introduced.
[ 308.986589] ------------[ cut here ]------------
[ 308.98
Wiz
CVE-2025-71083 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71083 [MEDIUM] CVE-2025-71083 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71083 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/ttm: Avoid NULL pointer deref for evicted BOs
It is possible for a BO to exist that is not currently associated with a
resource, e.g. because it has been evicted.
When devcoredump tries to read the contents of all BOs for dumping, we need
to expect this as well -- in this case, ENODATA is recorded instead of the
buffer contents.
Source : NVD
## 5.5
Score
Published January 13, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7
Exploitation Probability (EPSS) N/A
Wiz
CVE-2022-50747 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50747 CVE-2022-50747 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50747 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfs: Fix OOB Write in hfs_asc2mac
Syzbot reported a OOB Write bug:
## loop0: detected capacity change from 0 to 64
BUG: KASAN: slab-out-of-bounds in hfs_asc2mac+0x467/0x9a0
fs/hfs/trans.c:133
Write of size 1 at addr ffff88801848314e by task syz-executor391/3632
Call Trace: __dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x1b1/0x28e lib/dump_stack.c:106
print_address_description+0x74/0x340 mm/kasan/report.c:284
print_report+0x107/0x1f0 mm/kasan/report.c:395
kasan_report+0xcd/0x100 mm/kasan/report.c:495
hfs_asc2mac+0x467/0x9a0 fs/hfs/trans.c:133
hfs_cat_build_key+0x92/0x170 fs/hfs/catalog.c:28
hfs_lookup+0x1ab/0x2c0 fs/hfs/dir.c:31
looku
Wiz
CVE-2023-54100 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54100 CVE-2023-54100 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54100 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qedi: Fix use after free bug in qedi_remove()
In qedi_probe() we call __qedi_probe() which initializes
&qedi->recovery_work with qedi_recovery_handler() and
&qedi->board_disable_work with qedi_board_disable_work().
When qedi_schedule_recovery_handler() is called, schedule_delayed_work()
will finally start the work.
In qedi_remove(), which is called to remove the driver, the following
sequence may be observed:
Fix this by finishing the work before cleanup in qedi_remove().
CPU0 CPU1
|qedi_recovery_handler
qedi_remove |
__qedi_remove |
iscsi_host_free |
scsi_host_put |
//free shost |
|iscsi_host_for_each_session
|//use qedi->shost
Cancel
Wiz
CVE-2023-54280 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54280 CVE-2023-54280 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54280 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: fix potential race when tree connecting ipc
Protect access of TCP_Server_Info::hostname when building the ipc tree
name as it might get freed in cifsd thread and thus causing an
use-after-free bug in __tree_connect_dfs_target(). Also, while at it,
update status of IPC tcon on success and then avoid any extra tree
connects.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
Wiz
CVE-2026-23235 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23235 [HIGH] CVE-2026-23235 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23235 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
f2fs: fix out-of-bounds access in sysfs attribute read/write
Some f2fs sysfs attributes suffer from out-of-bounds memory access and
incorrect handling of integer values whose size is not 4 bytes.
For example:
vm:~# echo 65537 > /sys/fs/f2fs/vde/carve_out
vm:~# cat /sys/fs/f2fs/vde/carve_out
65537
vm:~# echo 4294967297 > /sys/fs/f2fs/vde/atgc_age_threshold
vm:~# cat /sys/fs/f2fs/vde/atgc_age_threshold
1
carve_out maps to {struct f2fs_sb_info}->carve_out, which is a 8-bit
integer. However, the sysfs interface allows setting it to a value
larger than 255, resulting in an out-of-range update.
atgc_age_threshold maps to {struct atgc_management}->age_t
Wiz
CVE-2026-23286 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23286 CVE-2026-23286 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23286 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
atm: lec: fix null-ptr-deref in lec_arp_clear_vccs
syzkaller reported a null-ptr-deref in lec_arp_clear_vccs().
This issue can be easily reproduced using the syzkaller reproducer.
In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by
multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc).
When the underlying VCC is closed, lec_vcc_close() iterates over all
ARP entries and calls lec_arp_clear_vccs() for each matched entry.
For example, when lec_vcc_close() iterates through the hlists in
priv->lec_arp_empty_ones or other ARP tables:
In the first iteration, for the first matched ARP entry sharing the VCC,lec_arp
Wiz
CVE-2023-54051 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54051 CVE-2023-54051 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54051 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: do not allow gso_size to be set to GSO_BY_FRAGS
One missing check in virtio_net_hdr_to_skb() allowed
syzbot to crash kernels again [1]
Do not allow gso_size to be set to GSO_BY_FRAGS (0xffff),
because this magic value is used by the kernel.
[1]
general protection fault, probably for non-canonical address 0xdffffc000000000e: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077]
CPU: 0 PID: 5039 Comm: syz-executor401 Not tainted 6.5.0-rc5-next-20230809-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023
RIP: 0010:skb_segment+0x1a52/0x3ef0 net/core/sk
Wiz
CVE-2025-68173 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68173 CVE-2025-68173 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68173 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ftrace: Fix softlockup in ftrace_module_enable
A soft lockup was observed when loading amdgpu module.
If a module has a lot of tracable functions, multiple calls
to kallsyms_lookup can spend too much time in RCU critical
section and with disabled preemption, causing kernel panic.
This is the same issue that was fixed in
commit d0b24b4e91fc ("ftrace: Prevent RCU stall on PREEMPT_VOLUNTARY
kernels") and commit 42ea22e754ba ("ftrace: Add cond_resched() to
ftrace_graph_set_hash()").
Fix it the same way by adding cond_resched() in ftrace_module_enable.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux
Wiz
CVE-2025-71195 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71195 CVE-2025-71195 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71195 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: xilinx: xdma: Fix regmap max_register
The max_register field is assigned the size of the register memory
region instead of the offset of the last register.
The result is that reading from the regmap via debugfs can cause
a segmentation fault:
tail /sys/kernel/debug/regmap/xdma.1.auto/registers
Unable to handle kernel paging request at virtual address ffff800082f70000
Mem abort info:
ESR = 0x0000000096000007
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x07: level 3 translation fault
[...]
Call trace:
regmap_mmio_read32le+0x10/0x30
_regmap_bus_reg_read+0x74/0xc0
_regmap_read+0x68/0x198
regmap_read+0x
Wiz
CVE-2026-23035 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23035 CVE-2026-23035 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23035 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Pass netdev to mlx5e_destroy_netdev instead of priv
mlx5e_priv is an unstable structure that can be memset(0) if profile
attaching fails.
Pass netdev to mlx5e_destroy_netdev() to guarantee it will work on a
valid netdev.
On mlx5e_remove: Check validity of priv->profile, before attempting
to cleanup any resources that might be not there.
This fixes a kernel oops in mlx5e_remove when switchdev mode fails due
to change profile failure.
$ devlink dev eswitch set pci/0000:00:03.0 mode switchdev
Error: mlx5_core: Failed setting eswitch to offloads.
dmesg:
workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR
mlx5_core 0012:03
Wiz
CVE-2022-50873 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50873 CVE-2022-50873 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50873 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vdpa/vp_vdpa: fix kfree a wrong pointer in vp_vdpa_remove
In vp_vdpa_remove(), the code kfree(&vp_vdpa_mgtdev->mgtdev.id_table) uses
a reference of pointer as the argument of kfree, which is the wrong pointer
and then may hit crash like this:
Unable to handle kernel paging request at virtual address 00ffff003363e30c
Internal error: Oops: 96000004 [#1] SMP
Call trace:
rb_next+0x20/0x5c
ext4_readdir+0x494/0x5c4 [ext4]
iterate_dir+0x168/0x1b4
__se_sys_getdents64+0x68/0x170
__arm64_sys_getdents64+0x24/0x30
el0_svc_common.constprop.0+0x7c/0x1bc
do_el0_svc+0x2c/0x94
el0_svc+0x20/0x30
el0_sync_handler+0xb0/0xb4
el0_sync+0x160/0x180
Code: 54000220 f9400441
Wiz
CVE-2026-23172 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.4
CVE-2026-23172 [HIGH] CVE-2026-23172 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23172 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: wwan: t7xx: fix potential skb->frags overflow in RX path
When receiving data in the DPMAIF RX path,
the t7xx_dpmaif_set_frag_to_skb() function adds
page fragments to an skb without checking if the number of
fragments has exceeded MAX_SKB_FRAGS. This could lead to a buffer overflow
in skb_shinfo(skb)->frags[] array, corrupting adjacent memory and
potentially causing kernel crashes or other undefined behavior.
This issue was identified through static code analysis by comparing with a
similar vulnerability fixed in the mt76 driver commit b102f0c522cf ("mt76:
fix array overflow on receiving too many fragments for a packet").
The vulnerability cou
Wiz
CVE-2026-23148 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-23148 [HIGH] CVE-2026-23148 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23148 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet: fix race in nvmet_bio_done() leading to NULL pointer dereference
There is a race condition in nvmet_bio_done() that can cause a NULL
pointer dereference in blk_cgroup_bio_start():
nvmet_bio_done() is called when a bio completes
nvmet_req_complete() is called, which invokes req->ops->queue_response(req)
The queue_response callback can re-queue and re-submit the same request
The re-submission reuses the same inline_bio from nvmet_req
Meanwhile, nvmet_req_bio_put() (called after nvmet_req_complete) invokes bio_uninit() for inline_bio, which sets bio->bi_blkg to NULL
The re-submitted bio enters submit_bio_noacct_nocheck()
blk_cgroup_bio_st
Wiz
CVE-2023-54116 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54116 CVE-2023-54116 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54116 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/fbdev-generic: prohibit potential out-of-bounds access
The fbdev test of IGT may write after EOF, which lead to out-of-bound
access for drm drivers with fbdev-generic. For example, run fbdev test
on a x86+ast2400 platform, with 1680x1050 resolution, will cause the
linux kernel hang with the following call trace:
Oops: 0000 [#1] PREEMPT SMP PTI
[IGT] fbdev: starting subtest eof
Workqueue: events drm_fb_helper_damage_work [drm_kms_helper]
[IGT] fbdev: starting subtest nullptr
RIP: 0010:memcpy_erms+0xa/0x20
RSP: 0018:ffffa17d40167d98 EFLAGS: 00010246
RAX: ffffa17d4eb7fa80 RBX: ffffa17d40e0aa80 RCX: 00000000000014c0
RDX: 0000000000001a40 RSI: ffff
Wiz
CVE-2026-23155 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23155 [MEDIUM] CVE-2026-23155 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23155 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_receive_bulk_callback(): fix error message
Sinc commit 79a6d1bfe114 ("can: gs_usb: gs_usb_receive_bulk_callback():
unanchor URL on usb_submit_urb() error") a failing resubmit URB will print
an info message.
In the case of a short read where netdev has not yet been assigned,
initialize as NULL to avoid dereferencing an undefined value. Also report
the error value of the failed resubmit.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Explo
Wiz
CVE-2026-23304 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23304 CVE-2026-23304 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23304 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu()
l3mdev_master_dev_rcu() can return NULL when the slave device is being
un-slaved from a VRF. All other callers deal with this, but we lost
the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu()
with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on
device with address").
KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f]
RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418)
Call Trace:
ip6_pol_route (net/ipv6/route.c:2318)
fib6_rule_lookup (net/ipv6/fib6_rules.c:115)
ip6_route_output_flags (net/ipv6/route.c:2607)
vrf_process_v6_outbound (drivers/ne
Wiz
CVE-2025-68265 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68265 CVE-2025-68265 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68265 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme: fix admin request_queue lifetime
The namespaces can access the controller's admin request_queue, and
stale references on the namespaces may exist after tearing down the
controller. Ensure the admin request_queue is active by moving the
controller's 'put' to after all controller references have been released
to ensure no one is can access the request_queue. This fixes a reported
use-after-free bug:
BUG: KASAN: slab-use-after-free in blk_queue_enter+0x41c/0x4a0
Read of size 8 at addr ffff88c0a53819f8 by task nvme/3287
CPU: 67 UID: 0 PID: 3287 Comm: nvme Tainted: G E 6.13.2-ga1582f1a031e #15
Tainted: [E]=UNSIGNED_MODULE
Hardware name: Jabil /EGS
Wiz
CVE-2026-23178 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23178 [HIGH] CVE-2026-23178 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23178 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: i2c-hid: fix potential buffer overflow in i2c_hid_get_report()
i2c_hid_xfer
recv_len + sizeof(__le16)
ihid->rawbuf
max_buffer_size
struct hid_ll_driver
The latter has size determined at runtime by the maximum size of
different report types you could receive on any particular device and
can be a much smaller value.
recv_len
ihid->bufsize - sizeof(__le16)
The impact is low since access to hidraw devices requires root.
Source : NVD
## 7.8
Score
Published February 14, 2026
Severity HIGH
CNA Score 7.8
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KE
Wiz
CVE-2023-53836 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53836 CVE-2023-53836 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53836 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf, sockmap: Fix skb refcnt race after locking changes
There is a race where skb's from the sk_psock_backlog can be referenced
after userspace side has already skb_consumed() the sk_buff and its refcnt
dropped to zer0 causing use after free.
The flow is the following:
while ((skb = skb_peek(&psock->ingress_skb))
sk_psock_handle_Skb(psock, skb, ..., ingress)
if (!ingress) ...
sk_psock_skb_ingress
sk_psock_skb_ingress_enqueue(skb)
msg->skb = skb
sk_psock_queue_msg(psock, msg)
skb_dequeue(&psock->ingress_skb)
The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is
what the application reads when recvmsg() is called. An application c
Wiz
CVE-2026-31393 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31393 CVE-2026-31393 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31393 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access
l2cap_information_rsp() checks that cmd_len covers the fixed
l2cap_info_rsp header (type + result, 4 bytes) but then reads
rsp->data without verifying that the payload is present:
L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads
4 bytes past the header (needs cmd_len >= 8).
L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header
(needs cmd_len >= 5).
A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an
out-of-bounds read of adjacent skb data.
Guard each data access with the required payload length check. If the
payload is too short, s
Wiz
CVE-2026-23370 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23370 CVE-2026-23370 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23370 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data
set_new_password() hex dumps the entire buffer, which contains plaintext
password data, including current and new passwords. Remove the hex dump
to avoid leaking credentials.
Source : NVD
## 4.4
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-6.17
linux-nvidia-lowlatency
Sources
NVD
Wiz
CVE-2025-71118 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71118 [MEDIUM] CVE-2025-71118 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71118 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ACPICA: Avoid walking the Namespace if start_node is NULL
Although commit 0c9992315e73 ("ACPICA: Avoid walking the ACPI Namespace
if it is not there") fixed the situation when both start_node and
acpi_gbl_root_node are NULL, the Linux kernel mainline now still crashed
on Honor Magicbook 14 Pro [1].
That happens due to the access to the member of parent_node in
acpi_ns_get_next_node(). The NULL pointer dereference will always
happen, no matter whether or not the start_node is equal to
ACPI_ROOT_OBJECT, so move the check of start_node being NULL
out of the if block.
Unfortunately, all the attempts to contact Honor have failed, they
refused to provid
Wiz
CVE-2026-23215 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23215 [MEDIUM] CVE-2026-23215 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23215 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/vmware: Fix hypercall clobbers
Fedora QA reported the following panic:
BUG: unable to handle page fault for address: 0000000040003e54
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20251119-3.fc43 11/19/2025
RIP: 0010:vmware_hypercall4.constprop.0+0x52/0x90
..
Call Trace:
vmmouse_report_events+0x13e/0x1b0
psmouse_handle_byte+0x15/0x60
ps2_interrupt+0x8a/0xd0
...
because the QEMU VMware mouse emulation is buggy, and clears the top 32
bits of %rdi that the kernel kept a pointer in.
The QEMU vmmouse driver saves and restores the register state i
Wiz
CVE-2025-68215 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68215 CVE-2025-68215 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68215 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: fix PTP cleanup on driver removal in error path
Improve the cleanup on releasing PTP resources in error path.
The error case might happen either at the driver probe and PTP
feature initialization or on PTP restart (errors in reset handling, NVM
update etc). In both cases, calls to PF PTP cleanup (ice_ptp_cleanup_pf
function) and 'ps_lock' mutex deinitialization were missed.
Additionally, ptp clock was not unregistered in the latter case.
Keep PTP state as 'uninitialized' on init to distinguish between error
scenarios and to avoid resource release duplication at driver removal.
The consequence of missing ice_ptp_cleanup_pf call is the followin
Wiz
CVE-2025-71090 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71090 [MEDIUM] CVE-2025-71090 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71090 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: fix nfsd_file reference leak in nfsd4_add_rdaccess_to_wrdeleg()
nfsd4_add_rdaccess_to_wrdeleg() unconditionally overwrites
fp->fi_fds[O_RDONLY] with a newly acquired nfsd_file. However, if
the client already has a SHARE_ACCESS_READ open from a previous OPEN
operation, this action overwrites the existing pointer without
releasing its reference, orphaning the previous reference.
Additionally, the function originally stored the same nfsd_file
pointer in both fp->fi_fds[O_RDONLY] and fp->fi_rdeleg_file with
only a single reference. When put_deleg_file() runs, it clears
fi_rdeleg_file and calls nfs4_file_put_access() to release the file.
However,
Wiz
CVE-2023-53839 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53839 CVE-2023-53839 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53839 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dccp: fix data-race around dp->dccps_mss_cache
dccp_sendmsg() reads dp->dccps_mss_cache before locking the socket.
Same thing in do_dccp_getsockopt().
Add READ_ONCE()/WRITE_ONCE() annotations,
and change dccp_sendmsg() to check again dccps_mss_cache
after socket is locked.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-mediatek
reiserfs-kmp-64kb
Sources
NVD
Debian 11
Wiz
CVE-2023-54317 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54317 CVE-2023-54317 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54317 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm flakey: don't corrupt the zero page
When we need to zero some range on a block device, the function
__blkdev_issue_zero_pages submits a write bio with the bio vector pointing
to the zero page. If we use dm-flakey with corrupt bio writes option, it
will corrupt the content of the zero page which results in crashes of
various userspace programs. Glibc assumes that memory returned by mmap is
zeroed and it uses it for calloc implementation; if the newly mapped
memory is not zeroed, calloc will return non-zeroed memory.
Fix this bug by testing if the page is equal to ZERO_PAGE(0) and
avoiding the corruption in this case.
Source : NVD
Published Dece
Wiz
CVE-2026-23444 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23444 CVE-2026-23444 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23444 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure
ieee80211_tx_prepare_skb() has three error paths, but only two of them
free the skb. The first error path (ieee80211_tx_prepare() returning
TX_DROP) does not free it, while invoke_tx_handlers() failure and the
fragmentation check both do.
Add kfree_skb() to the first error path so all three are consistent,
and remove the now-redundant frees in callers (ath9k, mt76,
mac80211_hwsim) to avoid double-free.
Document the skb ownership guarantee in the function's kdoc.
Source : NVD
## 6.5
Score
Published April 3, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux
Wiz
CVE-2025-68255 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68255 CVE-2025-68255 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68255 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8723bs: fix stack buffer overflow in OnAssocReq IE parsing
The Supported Rates IE length from an incoming Association Request frame
was used directly as the memcpy() length when copying into a fixed-size
16-byte stack buffer (supportRate). A malicious station can advertise an
IE length larger than 16 bytes, causing a stack buffer overflow.
Clamp ie_len to the buffer size before copying the Supported Rates IE,
and correct the bounds check when merging Extended Supported Rates to
prevent a second potential overflow.
This prevents kernel stack corruption triggered by malformed association
requests.
Source : NVD
## 7.5
Score
Publishe
Wiz
CVE-2026-23454 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23454 CVE-2026-23454 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23454 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown
A potential race condition exists in mana_hwc_destroy_channel() where
hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and
Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt
handler to dereference freed memory, leading to a use-after-free or
NULL pointer dereference in mana_hwc_handle_resp().
mana_smc_teardown_hwc() signals the hardware to stop but does not
synchronize against IRQ handlers already executing on other CPUs. The
IRQ synchronization only happens in mana_hwc_destroy_cq() via
mana_gd_destroy_eq() -> mana_gd_deregister_irq(
Wiz
CVE-2026-31395 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31395 CVE-2026-31395 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31395 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler
The ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER handler in
bnxt_async_event_process() uses a firmware-supplied 'type' field
directly as an index into bp->bs_trace[] without bounds validation.
The 'type' field is a 16-bit value extracted from DMA-mapped completion
ring memory that the NIC writes directly to host RAM. A malicious or
compromised NIC can supply any value from 0 to 65535, causing an
out-of-bounds access into kernel heap memory.
The bnxt_bs_trace_check_wrap() call then dereferences bs_trace->magic_byte
and writes to bs_trace->last_offset and bs_trace->wrapped, leading to
ker
Wiz
CVE-2025-71192 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71192 CVE-2025-71192 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71192 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: ac97: fix a double free in snd_ac97_controller_register()
If ac97_add_adapter() fails, put_device() is the correct way to drop
the device reference. kfree() is not required.
Add kfree() if idr_alloc() fails and in ac97_adapter_release() to do
the cleanup.
Found by code review.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-5.15
linux-riscv-6.8
Sources
NVD
Wiz
CVE-2026-23413 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23413 CVE-2026-23413 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23413 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clsact: Fix use-after-free in init/destroy rollback asymmetry
Fix a use-after-free in the clsact qdisc upon init/destroy rollback asymmetry.
The latter is achieved by first fully initializing a clsact instance, and
then in a second step having a replacement failure for the new clsact qdisc
instance. clsact_init() initializes ingress first and then takes care of the
egress part. This can fail midway, for example, via tcf_block_get_ext(). Upon
failure, the kernel will trigger the clsact_destroy() callback.
Commit 1cb6f0bae504 ("bpf: Fix too early release of tcx_entry") details the
way how the transition is happening. If tcf_block_get_ext on the q->in
Wiz
CVE-2025-71224 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71224 CVE-2025-71224 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71224 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: ocb: skip rx_no_sta when interface is not joined
ieee80211_ocb_rx_no_sta() assumes a valid channel context, which is only
present after JOIN_OCB.
RX may run before JOIN_OCB is executed, in which case the OCB interface
is not operational. Skip RX peer handling when the interface is not
joined to avoid warnings in the RX path.
Source : NVD
Published February 14, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 18.9
Exploitation Probability (EPSS) 0.1
Affected packages an
Wiz
CVE-2023-54252 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54252 CVE-2023-54252 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54252 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: think-lmi: Fix memory leaks when parsing ThinkStation WMI strings
My previous commit introduced a memory leak where the item allocated
from tlmi_setting was not freed.
This commit also renames it to avoid confusion with the similarly name
variable in the same function.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 8.6
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules-partner
kernel-debug-uki-
Wiz
CVE-2022-50732 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50732 CVE-2022-50732 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50732 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8192u: Fix use after free in ieee80211_rx()
We cannot dereference the "skb" pointer after calling
ieee80211_monitor_rx(), because it is a use after free.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-kvm
linux-aws-5.4
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added at: Dec 26, 2025
Ubuntu 14.04, 22.04 Severity MEDI
Wiz
CVE-2023-54056 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54056 CVE-2023-54056 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54056 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
kheaders: Use array declaration instead of char
Under CONFIG_FORTIFY_SOURCE, memcpy() will check the size of destination
and source buffers. Defining kernel_headers_data as "char" would trip
this check. Since these addresses are treated as byte arrays, define
them as arrays (as done everywhere else).
This was seen with:
$ cat /sys/kernel/kheaders.tar.xz >> /dev/null
detected buffer overflow in memcpy
kernel BUG at lib/string_helpers.c:1027!
...
RIP: 0010:fortify_panic+0xf/0x20
[...]
Call Trace: ikheaders_read+0x45/0x50 [kheaders]
kernfs_fop_read_iter+0x1a4/0x2f0
...
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Wiz
CVE-2023-53822 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53822 CVE-2023-53822 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53822 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: Ignore frags from uninitialized peer in dp.
When max virtual ap interfaces are configured in all the bands with
ACS and hostapd restart is done every 60s, a crash is observed at
random times.
In this certain scenario, a fragmented packet is received for
self peer, for which rx_tid and rx_frags are not initialized in
datapath. While handling this fragment, crash is observed as the
rx_frag list is uninitialised and when we walk in
ath11k_dp_rx_h_sort_frags, skb null leads to exception.
To address this, before processing received fragments we check
dp_setup_done flag is set to ensure that peer has completed its
dp peer setup for fragment
Wiz
CVE-2023-54118 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54118 CVE-2023-54118 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54118 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
serial: sc16is7xx: setup GPIO controller later in probe
The GPIO controller component of the sc16is7xx driver is setup too
early, which can result in a race condition where another device tries
to utilise the GPIO lines before the sc16is7xx device has finished
initialising.
This issue manifests itself as an Oops when the GPIO lines are configured:
Unable to handle kernel read from unreadable memory at virtual address
...
pc : sc16is7xx_gpio_direction_output+0x68/0x108 [sc16is7xx]
lr : sc16is7xx_gpio_direction_output+0x4c/0x108 [sc16is7xx]
...
Call trace:
sc16is7xx_gpio_direction_output+0x68/0x108 [sc16is7xx]
gpiod_direction_output_raw_commit+0x64/
Wiz
CVE-2025-68744 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68744 CVE-2025-68744 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68744 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Free special fields when update [lru_,]percpu_hash maps
As [lru_,]percpu_hash maps support BPF_KPTR_{REF,PERCPU}, missing
calls to 'bpf_obj_free_fields()' in 'pcpu_copy_value()' could cause the
memory referenced by BPF_KPTR_{REF,PERCPU} fields to be held until the
map gets freed.
Fix this by calling 'bpf_obj_free_fields()' after
'copy_map_value ,_long ' in 'pcpu_copy_value()'.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perce
Wiz
CVE-2025-68231 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68231 CVE-2025-68231 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68231 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/mempool: fix poisoning order>0 pages with HIGHMEM
The kernel test has reported:
BUG: unable to handle page fault for address: fffba000
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
*pde = 03171067 *pte = 00000000
Oops: Oops: 0002 [#1]
CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G T 6.18.0-rc2-00031-gec7f31b2a2d3 #1 NONE a1d066dfe789f54bc7645c7989957d2bdee593ca
Tainted: [T]=RANDSTRUCT
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
EIP: memset (arch/x86/include/asm/string_32.h:168 arch/x86/lib/memcpy_32.c:17)
Code: a5 8b 4d f4 83 e1 03 74 02 f3 a4 83 c4 04 5
Wiz
CVE-2025-71157 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71157 [HIGH] CVE-2025-71157 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71157 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/core: always drop device refcount in ib_del_sub_device_and_put()
Since nldev_deldev() (introduced by commit 060c642b2ab8 ("RDMA/nldev: Add
support to add/delete a sub IB device through netlink") grabs a reference
using ib_device_get_by_index() before calling ib_del_sub_device_and_put(),
we need to drop that reference before returning -EOPNOTSUPP error.
Source : NVD
## 7.8
Score
Published January 23, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.3
Exploitati
Wiz
CVE-2023-54050 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54050 CVE-2023-54050 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54050 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ubifs: Fix memleak when insert_old_idx() failed
Following process will cause a memleak for copied up znode:
dirty_cow_znode
zn = copy_znode(c, znode);
err = insert_old_idx(c, zbr->lnum, zbr->offs);
if (unlikely(err))
return ERR_PTR(err); // No one refers to zn.
Fetch a reproducer in [Link].
Function copy_znode() is split into 2 parts: resource allocation
and znode replacement, insert_old_idx() is split in similar way,
so resource cleanup could be done in error handling path without
corrupting metadata(mem & disk).
It's okay that old index inserting is put behind of add_idx_dirt(),
old index is used in layout_leb_in_gaps(), so the two processes do
Wiz
CVE-2025-68766 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68766 CVE-2025-68766 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68766 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
irqchip/mchp-eic: Fix error code in mchp_eic_domain_alloc()
If irq_domain_translate_twocell() sets "hwirq" to >= MCHP_EIC_NIRQ (2) then
it results in an out of bounds access.
The code checks for invalid values, but doesn't set the error code. Return
-EINVAL in that case, instead of returning success.
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-default-base
linux-az
Wiz
CVE-2025-68298 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68298 CVE-2025-68298 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68298 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: btusb: mediatek: Avoid btusb_mtk_claim_iso_intf() NULL deref
btmtk_data->isopkt_intf
That function can return NULL in some cases. Even when it returns
NULL, though, we still go on to call btusb_mtk_claim_iso_intf().
btmtk_data->isopkt_intf
btmtk_data->isopkt_intf
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules-core
kernel-rt-64k-devel-matche
Wiz
CVE-2022-50820 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50820 CVE-2022-50820 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50820 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
perf/arm_dmc620: Fix hotplug callback leak in dmc620_pmu_init()
dmc620_pmu_init() won't remove the callback added by
cpuhp_setup_state_multi() when platform_driver_register() failed. Remove
the callback by cpuhp_remove_multi_state() in fail path.
Similar to the handling of arm_ccn_init() in commit 26242b330093 ("bus:
arm-ccn: Prevent hotplug callback leak")
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Aff
Wiz
CVE-2022-50822 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50822 CVE-2022-50822 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50822 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/restrack: Release MR restrack when delete
The MR restrack also needs to be released when delete it, otherwise it
cause memory leak as the task struct won't be released.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
perf
linux-intel-iotg-5.15
Sources
NVD
Debian 11 No Fix Added at: Dec 31, 2025
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at:
Wiz
CVE-2023-54254 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54254 CVE-2023-54254 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54254 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/ttm: Don't leak a resource on eviction error
On eviction errors other than -EMULTIHOP we were leaking a resource.
Fix.
v2:
Avoid yet another goto (Andi Shyti)
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
kernel-64k-debug-devel-matched
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 8 Severit
Wiz
CVE-2026-33064 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.7
CVE-2026-33064 [HIGH] CVE-2026-33064 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-33064 :
Linux Ubuntu vulnerability analysis and mitigation
Free5GC is an open-source Linux Foundation project for 5th generation (5G) mobile core networks. Versions prior to 1.4.2 are vulnerable to procedure panic caused by Nil Pointer Dereference in the /sdm-subscriptions endpoint. A remote attacker can cause the UDM service to panic and crash by sending a crafted POST request to the /sdm-subscriptions endpoint with a malformed URL path containing path traversal sequences (../) and a large JSON payload. The DataChangeNotificationProcedure function in notifier.go attempts to access a nil pointer without proper validation, causing a complete service crash with "runtime error: invalid memory address or nil pointer dereference". Exploitation would result in UDM functionality dis
Wiz
CVE-2025-71161 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71161 [MEDIUM] CVE-2025-71161 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71161 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dm-verity: disable recursive forward error correction
There are two problems with the recursive correction:
It may cause denial-of-service. In fec_read_bufs, there is a loop thathas 253 iterations. For each iteration, we may call verity_hash_for_blockrecursively. There is a limit of 4 nested recursions - that means thatthere may be at most 253^4 (4 billion) iterations. Red Hat QE teamactually created an image that pushes dm-verity to this limit - and thisimage just makes the udev-worker process get stuck in the 'D' state.
It doesn't work. In fec_read_bufs we store data into the variable
"fio->bufs", but fio bufs is shared between recursive invoca
Wiz
CVE-2023-54208 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54208 CVE-2023-54208 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54208 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: ov5675: Fix memleak in ov5675_init_controls()
There is a kmemleak when testing the media/i2c/ov5675.c with bpf mock
device:
AssertionError: unreferenced object 0xffff888107362160 (size 16):
comm "python3", pid 277, jiffies 4294832798 (age 20.722s)
hex dump (first 16 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[] __kmalloc_node+0x44/0x1b0
[] kvmalloc_node+0x34/0x180
[] v4l2_ctrl_handler_init_class+0x11d/0x180
[videodev]
[] ov5675_probe+0x38b/0x897 [ov5675]
[] i2c_device_probe+0x28d/0x680
[] really_probe+0x17c/0x3f0
[] __driver_probe_device+0xe3/0x170
[] driver_probe_device+0x49/0x120
[] __device_attach_
Wiz
CVE-2023-54225 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54225 CVE-2023-54225 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54225 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ipa: only reset hashed tables when supported
Last year, the code that manages GSI channel transactions switched
from using spinlock-protected linked lists to using indexes into the
ring buffer used for a channel. Recently, Google reported seeing
transaction reference count underflows occasionally during shutdown.
Doug Anderson found a way to reproduce the issue reliably, and
bisected the issue to the commit that eliminated the linked lists
and the lock. The root cause was ultimately determined to be
related to unused transactions being committed as part of the modem
shutdown cleanup activity. Unused transactions are not normally
expected (exce
Wiz
CVE-2025-71132 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71132 [MEDIUM] CVE-2025-71132 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71132 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smc91x: fix broken irq-context in PREEMPT_RT
When smc91x.c is built with PREEMPT_RT, the following splat occurs
in FVP_RevC:
[ 13.055000] smc91x LNRO0003:00 eth0: link up, 10Mbps, half-duplex, lpa 0x0000
[ 13.062137] BUG: workqueue leaked atomic, lock or RCU: kworker/2:1[106]
[ 13.062137] preempt=0x00000000 lock=0->0 RCU=0->1 workfn=mld_ifc_work
[ 13.062266] C
** replaying previous printk message **
[ 13.062266] CPU: 2 UID: 0 PID: 106 Comm: kworker/2:1 Not tainted 6.18.0-dirty #179 PREEMPT_{RT,(full)}
[ 13.062353] Hardware name: , BIOS
[ 13.062382] Workqueue: mld mld_ifc_work
[ 13.062469] Call trace:
[ 13.062494] show_stack+0x24/0x40 (C)
[ 13.06260
Wiz
CVE-2023-54268 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54268 CVE-2023-54268 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54268 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
debugobjects: Don't wake up kswapd from fill_pool()
syzbot is reporting a lockdep warning in fill_pool() because the allocation
from debugobjects is using GFP_ATOMIC, which is (__GFP_HIGH | __GFP_KSWAPD_RECLAIM)
and therefore tries to wake up kswapd, which acquires kswapd_wait::lock.
Since fill_pool() might be called with arbitrary locks held, fill_pool()
should not assume that acquiring kswapd_wait::lock is safe.
Use __GFP_HIGH instead and remove __GFP_NORETRY as it is pointless for
!__GFP_DIRECT_RECLAIM allocation.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Wiz
CVE-2023-54260 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54260 CVE-2023-54260 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54260 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
cifs: Fix lost destroy smbd connection when MR allocate failed
If the MR allocate failed, the smb direct connection info is NULL,
then smbd_destroy() will directly return, then the connection info
will be leaked.
Let's set the smb direct connection info to the server before call
smbd_destroy().
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-64k-debug-modules
kern
Wiz
CVE-2023-53833 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53833 CVE-2023-53833 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53833 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/i915: Fix NULL ptr deref by checking new_crtc_state
intel_atomic_get_new_crtc_state can return NULL, unless crtc state wasn't
obtained previously with intel_atomic_get_crtc_state, so we must check it
for NULLness here, just as in many other places, where we can't guarantee
that intel_atomic_get_crtc_state was called.
We are currently getting NULL ptr deref because of that, so this fix was
confirmed to help.
(cherry picked from commit 1d5b09f8daf859247a1ea65b0d732a24d88980d8)
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release
Wiz
CVE-2023-54038 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54038 CVE-2023-54038 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54038 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_conn: return ERR_PTR instead of NULL when there is no link
hci_connect_sco currently returns NULL when there is no link (i.e. when
hci_conn_link() returns NULL).
sco_connect() expects an ERR_PTR in case of any error (see line 266 in
sco.c). Thus, hcon set as NULL passes through to sco_conn_add(), which
tries to get hcon->hdev, resulting in dereferencing a NULL pointer as
reported by syzkaller.
The same issue exists for iso_connect_cis() calling hci_connect_cis().
Thus, make hci_connect_sco() and hci_connect_cis() return ERR_PTR
instead of NULL.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux
Wiz
CVE-2025-68729 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68729 CVE-2025-68729 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68729 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath12k: Fix MSDU buffer types handling in RX error path
Currently, packets received on the REO exception ring from
unassociated peers are of MSDU buffer type, while the driver expects
link descriptor type packets. These packets are not parsed further due
to a return check on packet type in ath12k_hal_desc_reo_parse_err(),
but the associated skb is not freed. This may lead to kernel
crashes and buffer leaks.
Hence to fix, update the RX error handler to explicitly drop
MSDU buffer type packets received on the REO exception ring.
This prevents further processing of invalid packets and ensures
stability in the RX error handling path.
Tested-on:
Wiz
CVE-2026-23345 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23345 CVE-2026-23345 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23345 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64: gcs: Do not set PTE_SHARED on GCS mappings if FEAT_LPA2 is enabled
When FEAT_LPA2 is enabled, bits 8-9 of the PTE replace the
shareability attribute with bits 50-51 of the output address. The
_PAGE_GCS{,_RO} definitions include the PTE_SHARED bits as 0b11 (this
matches the other PAGE * definitions) but using this macro directly
leads to the following panic when enabling GCS on a system/model with
LPA2:
Unable to handle kernel paging request at virtual address fffff1ffc32d8008
Mem abort info:
ESR = 0x0000000096000004
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x04: level 0 translation fault
Data abort
Wiz
CVE-2025-71201 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2025-71201 [HIGH] CVE-2025-71201 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71201 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfs: Fix early read unlock of page with EOF in middle
The read result collection for buffered reads seems to run ahead of the
completion of subrequests under some circumstances, as can be seen in the
following log snippet:
9p_client_res: client 18446612686390831168 response P9_TREAD tag 0 err 0
...
netfs_sreq: R=00001b55[1] DOWN TERM f=192 s=0 5fb2/5fb2 s=5 e=0
...
netfs_collect_folio: R=00001b55 ix=00004 r=4000-5000 t=4000/5fb2
netfs_folio: i=157f3 ix=00004-00004 read-done
netfs_folio: i=157f3 ix=00004-00004 read-unlock
netfs_collect_folio: R=00001b55 ix=00005 r=5000-5fb2 t=5000/5fb2
netfs_folio: i=157f3 ix=00005-00005 read-done
netfs_folio: i=1
Wiz
CVE-2022-50880 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50880 CVE-2022-50880 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50880 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath10k: add peer map clean up for peer delete in ath10k_sta_state()
When peer delete failed in a disconnect operation, use-after-free
detected by KFENCE in below log. It is because for each vdev_id and
address, it has only one struct ath10k_peer, it is allocated in
ath10k_peer_map_event(). When connected to an AP, it has more than
one HTT_T2H_MSG_TYPE_PEER_MAP reported from firmware, then the
array peer_map of struct ath10k will be set muti-elements to the
same ath10k_peer in ath10k_peer_map_event(). When peer delete failed
in ath10k_sta_state(), the ath10k_peer will be free for the 1st peer
id in array peer_map of struct ath10k, and then use-
Wiz
CVE-2026-23081 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23081 [MEDIUM] CVE-2026-23081 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23081 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: phy: intel-xway: fix OF node refcount leakage
Automated review spotted am OF node reference count leakage when
checking if the 'leds' child node exists.
Call of_put_node() to correctly maintain the refcount.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.9
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug
kernel-rt-64k-devel
Sources
NVD
Debian 14 Severity MEDIUM Has Fix A
Wiz
CVE-2022-50850 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50850 CVE-2022-50850 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50850 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: ipr: Fix WARNING in ipr_init()
ipr_init() will not call unregister_reboot_notifier() when
pci_register_driver() fails, which causes a WARNING. Call
unregister_reboot_notifier() when pci_register_driver() fails.
notifier callback ipr_halt [ipr] already registered
WARNING: CPU: 3 PID: 299 at kernel/notifier.c:29
notifier_chain_register+0x16d/0x230
Modules linked in: ipr(+) xhci_pci_renesas xhci_hcd ehci_hcd usbcore
led_class gpu_sched drm_buddy video wmi drm_ttm_helper ttm
drm_display_helper drm_kms_helper drm drm_panel_orientation_quirks
agpgart cfbft
CPU: 3 PID: 299 Comm: modprobe Tainted: G W
6.1.0-rc1-00190-g39508d23b672-dirty #332
Hardware
Wiz
CVE-2023-54274 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54274 CVE-2023-54274 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54274 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/srpt: Add a check for valid 'mad_agent' pointer
When unregistering MAD agent, srpt module has a non-null check
for 'mad_agent' pointer before invoking ib_unregister_mad_agent().
This check can pass if 'mad_agent' variable holds an error value.
The 'mad_agent' can have an error value for a short window when
srpt_add_one() and srpt_remove_one() is executed simultaneously.
In srpt module, added a valid pointer check for 'sport->mad_agent'
before unregistering MAD agent.
This issue can hit when RoCE driver unregisters ib_device
## Stack Trace:
BUG: kernel NULL pointer dereference, address: 000000000000004d
PGD 145003067 P4D 145003067 PUD 2324
Wiz
CVE-2025-68774 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68774 CVE-2025-68774 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68774 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfsplus: fix missing hfs_bnode_get() in __hfs_bnode_create
When sync() and link() are called concurrently, both threads may
enter hfs_bnode_find() without finding the node in the hash table
and proceed to create it.
Thread A:
hfsplus_write_inode()
-> hfsplus_write_system_inode()
-> hfs_btree_write()
-> hfs_bnode_find(tree, 0)
-> __hfs_bnode_create(tree, 0)
Thread B:
hfsplus_create_cat()
-> hfs_brec_insert()
-> hfs_bnode_split()
-> hfs_bmap_alloc()
-> hfs_bnode_find(tree, 0)
-> __hfs_bnode_create(tree, 0)
In this case, thread A creates the bnode, sets refcnt=1, and hashes it.
Thread B also tries to create the same bnode, notices it has already
bee
Wiz
CVE-2023-54296 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54296 CVE-2023-54296 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54296 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: SVM: Get source vCPUs from source VM for SEV-ES intrahost migration
Fix a goof where KVM tries to grab source vCPUs from the destination VM
when doing intrahost migration. Grabbing the wrong vCPU not only hoses
the guest, it also crashes the host due to the VMSA pointer being left
NULL.
BUG: unable to handle page fault for address: ffffe38687000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 39 PID: 17143 Comm: sev_migrate_tes Tainted: GO 6.5.0-smp--fff2e47e6c3b-next #151
Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 34.28.0 07/10/2023
RIP: 001
Wiz
CVE-2023-54262 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54262 CVE-2023-54262 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54262 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Don't clone flow post action attributes second time
The code already clones post action attributes in
mlx5e_clone_flow_attr_for_post_act(). Creating another copy in
mlx5e_tc_post_act_add() is a erroneous leftover from original
implementation. Instead, assign handle->attribute to post_attr provided by
the caller. Note that cloning the attribute second time is not just
wasteful but also causes issues like second copy not being properly updated
in neigh update code which leads to following use-after-free:
Feb 21 09:02:00 c-237-177-40-045 kernel: BUG: KASAN: use-after-free in mlx5_cmd_set_fte+0x200d/0x24c0 [mlx5_core]
Feb 21 09:02:00 c-237-1
Wiz
CVE-2025-71238 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71238 [HIGH] CVE-2025-71238 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71238 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Fix bsg_done() causing double free
Kernel panic observed on system,
[5353358.825191] BUG: unable to handle page fault for address: ff5f5e897b024000
[5353358.825194] #PF: supervisor write access in kernel mode
[5353358.825195] #PF: error_code(0x0002) - not-present page
[5353358.825196] PGD 100006067 P4D 0
[5353358.825198] Oops: 0002 [#1] PREEMPT SMP NOPTI
[5353358.825200] CPU: 5 PID: 2132085 Comm: qlafwupdate.sub Kdump: loaded Tainted: G W L ------- --- 5.14.0-503.34.1.el9_5.x86_64 #1
[5353358.825203] Hardware name: HPE ProLiant DL360 Gen11/ProLiant DL360 Gen11, BIOS 2.44 01/17/2025
[5353358.825204] RIP: 0010:memcpy_erms+0x6/0x10
[535
Wiz
CVE-2026-33192 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.7
CVE-2026-33192 [HIGH] CVE-2026-33192 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-33192 :
Linux Ubuntu vulnerability analysis and mitigation
Free5GC is an open-source Linux Foundation project for 5th generation (5G) mobile core networks. In versions prior to 1.4.2, the UDM incorrectly converts a downstream 400 Bad Request (from UDR) into a 500 Internal Server Error when handling PATCH requests with an empty supi path parameter. Additionally, the UDM incorrectly translates the PATCH method to PUT when forwarding to UDR, indicating a deeper architectural issue. This leaks internal error handling behavior, making it difficult for clients to distinguish between client-side errors and server-side failures. The issue has been patched in version 1.4.2.
Source : NVD
## 8.7
Score
Published March 20, 2026
Severity HIGH
CNA Score 8.7
Affected Technologies
L
Wiz
CVE-2025-40343 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40343 CVE-2025-40343 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40343 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet-fc: avoid scheduling association deletion twice
When forcefully shutting down a port via the configfs interface,
nvmet_port_subsys_drop_link() first calls nvmet_port_del_ctrls() and
then nvmet_disable_port(). Both functions will eventually schedule all
remaining associations for deletion.
The current implementation checks whether an association is about to be
removed, but only after the work item has already been scheduled. As a
result, it is possible for the first scheduled work item to free all
resources, and then for the same work item to be scheduled again for
deletion.
Because the association list is an RCU list, it is not possible to t
Wiz
CVE-2023-54040 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54040 CVE-2023-54040 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54040 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: fix wrong fallback logic for FDIR
When adding a FDIR filter, if ice_vc_fdir_set_irq_ctx returns failure,
the inserted fdir entry will not be removed and if ice_vc_fdir_write_fltr
returns failure, the fdir context info for irq handler will not be cleared
which may lead to inconsistent or memory leak issue. This patch refines
failure cases to resolve this issue.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N
Wiz
CVE-2022-50744 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50744 CVE-2022-50744 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50744 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: lpfc: Fix hard lockup when reading the rx_monitor from debugfs
During I/O and simultaneous cat of /sys/kernel/debug/lpfc/fnX/rx_monitor, a
hard lockup similar to the call trace below may occur.
The spin_lock_bh in lpfc_rx_monitor_report is not protecting from timer
interrupts as expected, so change the strength of the spin lock to _irq.
Kernel panic - not syncing: Hard LOCKUP
CPU: 3 PID: 110402 Comm: cat Kdump: loaded
exception RIP: native_queued_spin_lock_slowpath+91
[IRQ stack]
native_queued_spin_lock_slowpath at ffffffffb814e30b
_raw_spin_lock at ffffffffb89a667a
lpfc_rx_monitor_record at ffffffffc0a73a36 [lpfc]
lpfc_cmf_timer at ffffff
Wiz
CVE-2022-50862 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50862 CVE-2022-50862 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50862 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: prevent decl_tag from being referenced in func_proto
Syzkaller was able to hit the following issue:
------------[ cut here ]------------
WARNING: CPU: 0 PID: 3609 at kernel/bpf/btf.c:1946
btf_type_id_size+0x2d5/0x9d0 kernel/bpf/btf.c:1946
Modules linked in:
CPU: 0 PID: 3609 Comm: syz-executor361 Not tainted
6.0.0-syzkaller-02734-g0326074ff465 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 09/22/2022
RIP: 0010:btf_type_id_size+0x2d5/0x9d0 kernel/bpf/btf.c:1946
Code: ef e8 7f 8e e4 ff 41 83 ff 0b 77 28 f6 44 24 10 18 75 3f e8 6d 91
e4 ff 44 89 fe bf 0e 00 00 00 e8 20 8e e4 ff e8 5b 91 e4 ff 0b 45
31 f6 e9 98 02
Wiz
CVE-2026-23179 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23179 CVE-2026-23179 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23179 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet-tcp: fixup hang in nvmet_tcp_listen_data_ready()
When the socket is closed while in TCP_LISTEN a callback is run to
flush all outstanding packets, which in turns calls
nvmet_tcp_listen_data_ready() with the sk_callback_lock held.
So we need to check if we are in TCP_LISTEN before attempting
to get the sk_callback_lock() to avoid a deadlock.
Source : NVD
Published February 14, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.4
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2025-71135 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71135 [MEDIUM] CVE-2025-71135 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71135 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md/raid5: fix possible null-pointer dereferences in raid5_store_group_thread_cnt()
The variable mddev->private is first assigned to conf and then checked:
conf = mddev->private;
if (!conf) ...
If conf is NULL, then mddev->private is also NULL. In this case,
null-pointer dereferences can occur when calling raid5_quiesce():
raid5_quiesce(mddev, true);
raid5_quiesce(mddev, false);
since mddev->private is assigned to conf again in raid5_quiesce(), and conf
is dereferenced in several places, for example:
conf->quiesce = 0;
wake_up(&conf->wait_for_quiescent);
To fix this issue, the function should unlock mddev and return before
invoking raid5_quiesc
Wiz
CVE-2025-68808 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68808 CVE-2025-68808 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68808 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: vidtv: initialize local pointers upon transfer of memory ownership
vidtv_channel_si_init() creates a temporary list (program, service, event)
and ownership of the memory itself is transferred to the PAT/SDT/EIT
tables through vidtv_psi_pat_program_assign(),
vidtv_psi_sdt_service_assign(), vidtv_psi_eit_event_assign().
The problem here is that the local pointer where the memory ownership
transfer was completed is not initialized to NULL. This causes the
vidtv_psi_pmt_create_sec_for_each_pat_entry() function to fail, and
in the flow that jumps to free_eit, the memory that was freed by
vidtv_psi_ table_destroy() can be accessed again by
vidtv_p
Wiz
CVE-2025-68767 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68767 CVE-2025-68767 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68767 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfsplus: Verify inode mode when loading from disk
syzbot is reporting that S_IFMT bits of inode->i_mode can become bogus when
the S_IFMT bits of the 16bits "mode" field loaded from disk are corrupted.
According to [1], the permissions field was treated as reserved in Mac OS
8 and 9. According to [2], the reserved field was explicitly initialized
with 0, and that field must remain 0 as long as reserved. Therefore, when
the "mode" field is not 0 (i.e. no longer reserved), the file must be
S_IFDIR if dir == 1, and the file must be one of S_IFREG/S_IFLNK/S_IFCHR/
S_IFBLK/S_IFIFO/S_IFSOCK if dir == 0.
Source : NVD
Published January 13, 2026
CNA Score
Wiz
CVE-2025-68801 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68801 CVE-2025-68801 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68801 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mlxsw: spectrum_router: Fix neighbour use-after-free
We sometimes observe use-after-free when dereferencing a neighbour [1].
The problem seems to be that the driver stores a pointer to the
neighbour, but without holding a reference on it. A reference is only
taken when the neighbour is used by a nexthop.
Fix by simplifying the reference counting scheme. Always take a
reference when storing a neighbour pointer in a neighbour entry. Avoid
taking a referencing when the neighbour is used by a nexthop as the
neighbour entry associated with the nexthop already holds a reference.
Tested by running the test that uncovered the problem over 300 times.
Witho
Wiz
CVE-2023-54088 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54088 CVE-2023-54088 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54088 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blk-cgroup: hold queue_lock when removing blkg->q_node
When blkg is removed from q->blkg_list from blkg_free_workfn(), queue_lock
has to be held, otherwise, all kinds of bugs(list corruption, hard lockup,
..) can be triggered from blkg_destroy_all().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-fde
kernel-kvmsmall
Sources
NVD
Debian 12 No Fix Added at: Dec 2
Wiz
CVE-2025-68299 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68299 CVE-2025-68299 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68299 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
afs: Fix delayed allocation of a cell's anonymous key
The allocation of a cell's anonymous key is done in a background thread
along with other cell setup such as doing a DNS upcall. In the reported
bug, this is triggered by afs_parse_source() parsing the device name given
to mount() and calling afs_lookup_cell() with the name of the cell.
The normal key lookup then tries to use the key description on the
anonymous authentication key as the reference for request_key() - but it
may not yet be set and so an oops can happen.
This has been made more likely to happen by the fix for dynamic lookup
failure.
Fix this by firstly allocating a reference name
Wiz
CVE-2025-68285 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68285 CVE-2025-68285 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68285 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: fix potential use-after-free in have_mon_and_osd_map()
The wait loop in __ceph_open_session() can race with the client
receiving a new monmap or osdmap shortly after the initial map is
received. Both ceph_monc_handle_map() and handle_one_map() install
a new map immediately after freeing the old one
kfree(monc->monmap);
monc->monmap = monmap;
ceph_osdmap_destroy(osdc->osdmap);
osdc->osdmap = newmap;
under client->monc.mutex and client->osdc.lock respectively, but
because neither is taken in have_mon_and_osd_map() it's possible for
client->monc.monmap->epoch and client->osdc.osdmap->epoch arms in
client->monc.monmap && client->monc.monmap
Wiz
CVE-2025-68822 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68822 CVE-2025-68822 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68822 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Input: alps - fix use-after-free bugs caused by dev3_register_work
The dev3_register_work delayed work item is initialized within
alps_reconnect() and scheduled upon receipt of the first bare
PS/2 packet from an external PS/2 device connected to the ALPS
touchpad. During device detachment, the original implementation
calls flush_workqueue() in psmouse_disconnect() to ensure
completion of dev3_register_work. However, the flush_workqueue()
in psmouse_disconnect() only blocks and waits for work items that
were already queued to the workqueue prior to its invocation. Any
work items submitted after flush_workqueue() is called are not
included in the set
Wiz
CVE-2023-54240 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54240 CVE-2023-54240 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54240 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_hwlro_get_fdir_all()
rule_locs is allocated in ethtool_get_rxnfc and the size is determined by
rule_cnt from user space. So rule_cnt needs to be check before using
rule_locs to avoid NULL pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-xilinx
kernel-livepatch-6_4_0-150600_23_84-
Wiz
CVE-2026-23210 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23210 [MEDIUM] CVE-2026-23210 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23210 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ice: Fix PTP NULL pointer dereference during VSI rebuild
Fix race condition where PTP periodic work runs while VSI is being
rebuilt, accessing NULL vsi->rx_rings.
The sequence was:
ice_ptp_prepare_for_reset() cancels PTP work
ice_ptp_rebuild() immediately queues PTP work
VSI rebuild happens AFTER ice_ptp_rebuild()
PTP work runs and accesses NULL vsi->rx_rings
Fix: Keep PTP work cancelled during rebuild, only queue it after
VSI rebuild completes in ice_rebuild().
Added ice_ptp_queue_work() helper function to encapsulate the logic
for queuing PTP work, ensuring it's only queued when PTP is supported
and the state is ICE_PTP_READY.
Error log:
[
Wiz
CVE-2026-23036 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23036 CVE-2026-23036 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23036 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: release path before iget_failed() in btrfs_read_locked_inode()
In btrfs_read_locked_inode() if we fail to lookup the inode, we jump to
the 'out' label with a path that has a read locked leaf and then we call
iget_failed(). This can result in a ABBA deadlock, since iget_failed()
triggers inode eviction and that causes the release of the delayed inode,
which must lock the delayed inode's mutex, and a task updating a delayed
inode starts by taking the node's mutex and then modifying the inode's
subvolume btree.
Syzbot reported the following lockdep splat for this:
## ======================================================
WARNING: possible cir
Wiz
CVE-2023-53861 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53861 CVE-2023-53861 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53861 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: correct grp validation in ext4_mb_good_group
Group corruption check will access memory of grp and will trigger kernel
crash if grp is NULL. So do NULL check before corruption check.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-hisilicon
kernel-docs-html
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 09, 2025
Echo Has Fix Added at: Dec 09, 2025
Red H
Wiz
CVE-2026-23129 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23129 [MEDIUM] CVE-2026-23129 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23129 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dpll: Prevent duplicate registrations
Modify the internal registration helpers dpll_xa_ref_{dpll,pin}_add()
to reject duplicate registration attempts.
Previously, if a caller attempted to register the same pin multiple
times (with the same ops, priv, and cookie) on the same device, the core
silently increments the reference count and return success. This behavior
is incorrect because if the caller makes these duplicate registrations
then for the first one dpll_pin_registration is allocated and for others
the associated dpll_pin_ref.refcount is incremented. During the first
unregistration the associated dpll_pin_registration is freed and for
others
Wiz
CVE-2025-68325 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68325 CVE-2025-68325 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68325 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: sch_cake: Fix incorrect qlen reduction in cake_drop
In cake_drop(), qdisc_tree_reduce_backlog() is used to update the qlen
and backlog of the qdisc hierarchy. Its caller, cake_enqueue(), assumes
that the parent qdisc will enqueue the current packet. However, this
assumption breaks when cake_enqueue() returns NET_XMIT_CN: the parent
qdisc stops enqueuing current packet, leaving the tree qlen/backlog
accounting inconsistent. This mismatch can lead to a NULL dereference
(e.g., when the parent Qdisc is qfq_qdisc).
This patch computes the qlen/backlog delta in a more robust way by
observing the difference before and after the series of cake_d
Wiz
CVE-2025-40354 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40354 CVE-2025-40354 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40354 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amd/display: increase max link count and fix link->enc NULL pointer access
[why]
1.) dc->links[MAX_LINKS] array size smaller than actual requested.
max_connector + max_dpia + 4 virtual = 14.
increase from 12 to 14.
2.) hw_init() access null LINK_ENC for dpia non display_endpoint.
(cherry picked from commit d7f5a61e1b04ed87b008c8d327649d184dc5bb45)
Source : NVD
## 6.2
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitatio
Wiz
CVE-2026-23095 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-23095 [HIGH] CVE-2026-23095 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23095 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gue: Fix skb memleak with inner IP protocol 0.
syzbot reported skb memleak below. [0]
The repro generated a GUE packet with its inner protocol 0.
gue_udp_recv() returns -guehdr->proto_ctype for "resubmit"
in ip_protocol_deliver_rcu(), but this only works with
non-zero protocol number.
Let's drop such packets.
Note that 0 is a valid number (IPv6 Hop-by-Hop Option).
I think it is not practical to encap HOPOPT in GUE, so once
someone starts to complain, we could pass down a resubmit
flag pointer to distinguish two zeros from the upper layer:
no error
resubmit HOPOPT
[0]
BUG: memory leak
unreferenced object 0xffff888109695a00 (size 240):comm "syz
Wiz
CVE-2026-23386 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23386 CVE-2026-23386 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23386 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gve: fix incorrect buffer cleanup in gve_tx_clean_pending_packets for QPL
In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA
buffer cleanup path. It iterates num_bufs times and attempts to unmap
entries in the dma array.
This leads to two issues:
The dma array shares storage with tx_qpl_buf_ids (union).
Interpreting buffer IDs as DMA addresses results in attempting to
unmap incorrect memory locations.
2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed
the size of the dma array, causing out-of-bounds access warnings
(trace below is how we noticed this issue).
UBSAN: array-index-out-of-bounds in
drivers/net/
Wiz
CVE-2025-71233 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71233 [MEDIUM] CVE-2025-71233 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71233 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI: endpoint: Avoid creating sub-groups asynchronously
The asynchronous creation of sub-groups by a delayed work could lead to a
NULL pointer dereference when the driver directory is removed before the
work completes.
The crash can be easily reproduced with the following commands:
## cd /sys/kernel/config/pci_ep/functions/pci_epf_test
## for i in {1..20}; do mkdir test && rmdir test; done
BUG: kernel NULL pointer dereference, address: 0000000000000088
...
Call Trace:
configfs_register_group+0x3d/0x190
pci_epf_cfs_work+0x41/0x110
process_one_work+0x18f/0x350
worker_thread+0x25a/0x3a0
Fix this issue by using configfs_add_default_group() API w
Wiz
CVE-2026-23069 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23069 [MEDIUM] CVE-2026-23069 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23069 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vsock/virtio: fix potential underflow in virtio_transport_get_credit()
The credit calculation in virtio_transport_get_credit() uses unsigned
arithmetic:
ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
If the peer shrinks its advertised buffer (peer_buf_alloc) while bytes
are in flight, the subtraction can underflow and produce a large
positive value, potentially allowing more data to be queued than the
peer can handle.
Reuse virtio_transport_has_space() which already handles this case and
add a comment to make it clear why we are doing that.
[Stefano: use virtio_transport_has_space() instead of duplicating the code]
[Stefano: twea
Wiz
CVE-2025-71199 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71199 CVE-2025-71199 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71199 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iio: adc: at91-sama5d2_adc: Fix potential use-after-free in sama5d2_adc driver
at91_adc_interrupt can call at91_adc_touch_data_handler function
to start the work by schedule_work(&st->touch_st.workq).
If we remove the module which will call at91_adc_remove to
make cleanup, it will free indio_dev through iio_device_unregister but
quite a bit later. While the work mentioned above will be used. The
sequence of operations that may lead to a UAF bug is as follows:
CPU0 CPU1
| at91_adc_workq_handler
at91_adc_remove |
iio_device_unregister(indio_dev) |
//free indio_dev a bit later |
| iio_push_to_buffers(indio_dev)
| //use indio_dev
Fix it by ensuring
Wiz
CVE-2026-23162 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23162 [HIGH] CVE-2026-23162 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23162 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/nvm: Fix double-free on aux add failure
After a successful auxiliary_device_init(), aux_dev->dev.release
(xe_nvm_release_dev()) is responsible for the kfree(nvm). When
there is failure with auxiliary_device_add(), driver will call
auxiliary_device_uninit(), which call put_device(). So that the
.release callback will be triggered to free the memory associated
with the auxiliary_device.
Move the kfree(nvm) into the auxiliary_device_init() failure path
and remove the err goto path to fix below error.
"
[ 13.232905] ==================================================================
[ 13.232911] BUG: KASAN: double-free in xe_nvm_init+0x751/0xf10
Wiz
CVE-2025-68743 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68743 CVE-2025-68743 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68743 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mshv: Fix create memory region overlap check
The current check is incorrect; it only checks if the beginning or end
of a region is within an existing region. This doesn't account for
userspace specifying a region that begins before and ends after an
existing region.
Change the logic to a range intersection check against gfns and uaddrs
for each region.
Remove mshv_partition_region_by_uaddr() as it is no longer used.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Pe
Wiz
CVE-2025-68312 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68312 CVE-2025-68312 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68312 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usbnet: Prevents free active kevent
The root cause of this issue are:
When probing the usbnet device, executing usbnet_link_change(dev, 0, 0);put the kevent work in global workqueue. However, the kevent has not yetbeen scheduled when the usbnet device is unregistered. Therefore, executingfree_netdev() results in the "free active object (kevent)" error reportedhere.
Another factor is that when calling usbnet_disconnect()->unregister_netdev(),
if the usbnet device is up, ndo_stop() is executed to cancel the kevent.
However, because the device is not up, ndo_stop() is not executed.
The solution to this problem is to cancel the kevent before executi
Wiz
CVE-2023-53830 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53830 CVE-2023-53830 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53830 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: think-lmi: Fix memory leak when showing current settings
When retriving a item string with tlmi_setting(), the result has to be
freed using kfree(). In current_value_show() however, malformed
item strings are not freed, causing a memory leak.
Fix this by eliminating the early return responsible for this.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
ocfs2-kmp-de
Wiz
CVE-2025-68732 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68732 CVE-2025-68732 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68732 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
gpu: host1x: Fix race in syncpt alloc/free
Fix race condition between host1x_syncpt_alloc()
and host1x_syncpt_put() by using kref_put_mutex()
instead of kref_put() + manual mutex locking.
This ensures no thread can acquire the
syncpt_mutex after the refcount drops to zero
but before syncpt_release acquires it.
This prevents races where syncpoints could
be allocated while still being cleaned up
from a previous release.
Remove explicit mutex locking in syncpt_release
as kref_put_mutex() handles this atomically.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Marine
Wiz
CVE-2023-54266 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54266 CVE-2023-54266 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54266 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
media: dvb-usb: m920x: Fix a potential memory leak in m920x_i2c_xfer()
'read' is freed when it is known to be NULL, but not when a read error
occurs.
Revert the logic to avoid a small leak, should a m920x_read() call fail.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-mediatek
linux-oracle-5.15
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo
Wiz
CVE-2025-71198 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71198 CVE-2025-71198 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71198 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iio: imu: st_lsm6dsx: fix iio_chan_spec for sensors without event detection
The st_lsm6dsx_acc_channels array of struct iio_chan_spec has a non-NULL
event_spec field, indicating support for IIO events. However, event
detection is not supported for all sensors, and if userspace tries to
configure accelerometer wakeup events on a sensor device that does not
support them (e.g. LSM6DS0), st_lsm6dsx_write_event() dereferences a NULL
pointer when trying to write to the wakeup register.
Define an additional struct iio_chan_spec array whose members have a NULL
event_spec field, and use this array instead of st_lsm6dsx_acc_channels for
sensors without event
Wiz
CVE-2025-68261 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68261 CVE-2025-68261 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68261 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: add i_data_sem protection in ext4_destroy_inline_data_nolock()
Fix a race between inline data destruction and block mapping.
The function ext4_destroy_inline_data_nolock() changes the inode data
layout by clearing EXT4_INODE_INLINE_DATA and setting EXT4_INODE_EXTENTS.
At the same time, another thread may execute ext4_map_blocks(), which
tests EXT4_INODE_EXTENTS to decide whether to call ext4_ext_map_blocks()
or ext4_ind_map_blocks().
Without i_data_sem protection, ext4_ind_map_blocks() may receive inode
with EXT4_INODE_EXTENTS flag and triggering assert.
kernel BUG at fs/ext4/indirect.c:546!
EXT4-fs (loop2): unmounting filesystem.
invalid o
Wiz
CVE-2023-54301 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54301 CVE-2023-54301 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54301 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
brcmuart_probe
Smatch reports:
drivers/tty/serial/8250/8250_bcm7271.c:1120 brcmuart_probe() warn:
'baud_mux_clk' from clk_prepare_enable() not released on lines: 1032.
The issue is fixed by using a managed clock.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k
kernel-64k-debug-devel-matched
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has
Wiz
CVE-2025-71096 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71096 [MEDIUM] CVE-2025-71096 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71096 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/core: Check for the presence of LS_NLA_TYPE_DGID correctly
The netlink response for RDMA_NL_LS_OP_IP_RESOLVE should always have a
LS_NLA_TYPE_DGID attribute, it is invalid if it does not.
Use the nl parsing logic properly and call nla_parse_deprecated() to fill
the nlattrs array and then directly index that array to get the data for
the DGID. Just fail if it is NULL.
Remove the for loop searching for the nla, and squash the validation and
parsing into one function.
Fixes an uninitialized read from the stack triggered by userspace if it
does not provide the DGID to a kernel initiated RDMA_NL_LS_OP_IP_RESOLVE
query.
BUG: KMSAN: uninit-value i
Wiz
CVE-2026-23204 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.1
CVE-2026-23204 [HIGH] CVE-2026-23204 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23204 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: cls_u32: use skb_header_pointer_careful()
skb_header_pointer() does not fully validate negative @offset values.
Use skb_header_pointer_careful() instead.
GangMin Kim provided a report and a repro fooling u32_classify():
BUG: KASAN: slab-out-of-bounds in u32_classify+0x1180/0x11b0
net/sched/cls_u32.c:221
Source : NVD
## 7.1
Score
Published February 14, 2026
Severity HIGH
CNA Score 7.1
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.3
Exploitation Probability (EPSS) N/A
Affected packag
Wiz
CVE-2026-23216 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23216 [HIGH] CVE-2026-23216 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23216 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: iscsi: Fix use-after-free in iscsit_dec_conn_usage_count()
In iscsit_dec_conn_usage_count(), the function calls complete() while
holding the conn->conn_usage_lock. As soon as complete() is invoked, the
waiter (such as iscsit_close_connection()) may wake up and proceed to free
the iscsit_conn structure.
If the waiter frees the memory before the current thread reaches
spin_unlock_bh(), it results in a KASAN slab-use-after-free as the function
attempts to release a lock within the already-freed connection structure.
Fix this by releasing the spinlock before calling complete().
Source : NVD
## 7.8
Score
Published February 18, 2026
Wiz
CVE-2022-50709 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50709 CVE-2022-50709 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50709 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath9k: avoid uninit memory read in ath9k_htc_rx_msg()
syzbot is reporting uninit value at ath9k_htc_rx_msg() [1], for
ioctl(USB_RAW_IOCTL_EP_WRITE) can call ath9k_hif_usb_rx_stream() with
pkt_len = 0 but ath9k_hif_usb_rx_stream() uses
__dev_alloc_skb(pkt_len + 32, GFP_ATOMIC) based on an assumption that
pkt_len is valid. As a result, ath9k_hif_usb_rx_stream() allocates skb
with uninitialized memory and ath9k_htc_rx_msg() is reading from
uninitialized memory.
Since bytes accessed by ath9k_htc_rx_msg() is not known until
ath9k_htc_rx_msg() is called, it would be difficult to check minimal valid
pkt_len at "if (pkt_len > 2 * MAX_RX_BUF_SIZE) {"
Wiz
CVE-2025-71137 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71137 [HIGH] CVE-2025-71137 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71137 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
octeontx2-pf: fix "UBSAN: shift-out-of-bounds error"
This patch ensures that the RX ring size (rx_pending) is not
set below the permitted length. This avoids UBSAN
shift-out-of-bounds errors when users passes small or zero
ring sizes via ethtool -G.
Source : NVD
## 7.8
Score
Published January 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-modules-extra
kernel-64k
Sources
Wiz
CVE-2022-50716 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50716 CVE-2022-50716 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50716 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ar5523: Fix use-after-free on ar5523_cmd() timed out
syzkaller reported use-after-free with the stack trace like below [1]:
[ 38.960489][ C3] ==================================================================
[ 38.963216][ C3] BUG: KASAN: use-after-free in ar5523_cmd_tx_cb+0x220/0x240
[ 38.964950][ C3] Read of size 8 at addr ffff888048e03450 by task swapper/3/0
[ 38.966363][ C3]
[ 38.967053][ C3] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 6.0.0-09039-ga6afa4199d3d-dirty #18
[ 38.968464][ C3] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014
[ 38.969959][ C3] Call Trace:
[ 38.970841][ C3] [ 38.971663][ C3] dum
Wiz
CVE-2026-23116 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23116 [MEDIUM] CVE-2026-23116 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23116 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pmdomain: imx8m-blk-ctrl: Remove separate rst and clk mask for 8mq vpu
For i.MX8MQ platform, the ADB in the VPUMIX domain has no separate reset
and clock enable bits, but is ungated and reset together with the VPUs.
So we can't reset G1 or G2 separately, it may led to the system hang.
Remove rst_mask and clk_mask of imx8mq_vpu_blk_ctl_domain_data.
Let imx8mq_vpu_power_notifier() do really vpu reset.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2026-23177 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23177 CVE-2026-23177 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23177 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm, shmem: prevent infinite loop on truncate race
When truncating a large swap entry, shmem_free_swap() returns 0 when the
entry's index doesn't match the given index due to lookup alignment. The
failure fallback path checks if the entry crosses the end border and
aborts when it happens, so truncate won't erase an unexpected entry or
range. But one scenario was ignored.
index
indices[0]
index
indices[0]
The next iteration will find the same entry again at the same index with
same indices, leading to an infinite loop.
Fix this by retrying with a round-down index, and abort if the index is
smaller than the truncate range.
Source : NVD
Publishe
Wiz
CVE-2026-22994 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22994 [MEDIUM] CVE-2026-22994 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22994 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix reference count leak in bpf_prog_test_run_xdp()
syzbot is reporting
unregister_netdevice: waiting for sit0 to become free. Usage count = 2
problem. A debug printk() patch found that a refcount is obtained at
xdp_convert_md_to_buff() from bpf_prog_test_run_xdp().
According to commit ec94670fcb3b ("bpf: Support specifying ingress via
xdp_md context in BPF_PROG_TEST_RUN"), the refcount obtained by
xdp_convert_md_to_buff() will be released by xdp_convert_buff_to_md().
Therefore, we can consider that the error handling path introduced by
commit 1c1949982524 ("bpf: introduce frags support to
bpf_prog_test_run_xdp()") forgot to call xdp_conver
Wiz
CVE-2023-54149 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54149 CVE-2023-54149 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54149 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses
When using the felix driver (the only one which supports UC filtering
and MC filtering) as a DSA master for a random other DSA switch, one can
see the following stack trace when the downstream switch ports join a
VLAN-aware bridge:
## =============================
WARNING: suspicious RCU usage
net/8021q/vlan_core.c:238 suspicious rcu_dereference_protected() usage!
stack backtrace:
Workqueue: dsa_ordered dsa_slave_switchdev_event_work
Call trace:
lockdep_rcu_suspicious+0x170/0x210
vlan_for_each+0x8c/0x188
dsa_slave_sync_uc+0x128/0x178
__hw_addr_sync_dev+0x138/0x158
dsa_slav
Wiz
CVE-2026-23139 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-23139 [HIGH] CVE-2026-23139 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23139 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conncount: update last_gc only when GC has been performed
Currently last_gc is being updated everytime a new connection is
tracked, that means that it is updated even if a GC wasn't performed.
With a sufficiently high packet rate, it is possible to always bypass
the GC, causing the list to grow infinitely.
Update the last_gc value only when a GC has been actually performed.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score 7.5
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabilit
Wiz
CVE-2023-54048 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54048 CVE-2023-54048 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54048 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/bnxt_re: Prevent handling any completions after qp destroy
HW may generate completions that indicates QP is destroyed.
Driver should not be scheduling any more completion handlers
for this QP, after the QP is destroyed. Since CQs are active
during the QP destroy, driver may still schedule completion
handlers. This can cause a race where the destroy_cq and poll_cq
running simultaneously.
Snippet of kernel panic while doing bnxt_re driver load unload in loop.
This indicates a poll after the CQ is freed.
[77786.481636] Call Trace:
[77786.481640] [77786.481644] bnxt_re_poll_cq+0x14a/0x620 [bnxt_re]
[77786.481658] ? kvm_clock_read+0x14/0x30
[77786
Wiz
CVE-2025-68218 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68218 CVE-2025-68218 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68218 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-multipath: fix lockdep WARN due to partition scan work
Blktests test cases nvme/014, 057 and 058 fail occasionally due to a
lockdep WARN. As reported in the Closes tag URL, the WARN indicates that
a deadlock can happen due to the dependency among disk->open_mutex,
kblockd workqueue completion and partition_scan_work completion.
To avoid the lockdep WARN and the potential deadlock, cut the dependency
by running the partition_scan_work not by kblockd workqueue but by
nvme_wq.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Relea
Wiz
CVE-2026-23208 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23208 [HIGH] CVE-2026-23208 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23208 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: usb-audio: Prevent excessive number of frames
In this case, the user constructed the parameters with maxpacksize 40
for rate 22050 / pps 1000, and packsize[0] 22 packsize[1] 23. The buffer
size for each data URB is maxpacksize * packets, which in this example
is 40 * 6 = 240; When the user performs a write operation to send audio
data into the ALSA PCM playback stream, the calculated number of frames
is packsize[0] * packets = 264, which exceeds the allocated URB buffer
size, triggering the out-of-bounds (OOB) issue reported by syzbot [1].
Added a check for the number of single data URB frames when calculating
the number of frames to prevent
Wiz
CVE-2025-68178 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68178 CVE-2025-68178 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68178 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
blk-cgroup: fix possible deadlock while configuring policy
Following deadlock can be triggered easily by lockdep:
## WARNING: possible circular locking dependency detected
6.17.0-rc3-00124-ga12c2658ced0 #1665 Not tainted
check/1334 is trying to acquire lock:
ff1100011d9d0678 (&q->sysfs_lock){+.+.}-{4:4}, at: blk_unregister_queue+0x53/0x180
but task is already holding lock:
ff1100011d9d00e0 (&q->q_usage_counter(queue)#3){++++}-{0:0}, at: del_gendisk+0xba/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (&q->q_usage_counter(queue)#3){++++}-{0:0}:
blk_queue_enter+0x40b/0x470
blkg_conf_
Wiz
CVE-2025-68342 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68342 CVE-2025-68342 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68342 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing data
The URB received in gs_usb_receive_bulk_callback() contains a struct
gs_host_frame. The length of the data after the header depends on the
gs_host_frame hf::flags and the active device features (e.g. time
stamping).
Introduce a new function gs_usb_get_minimum_length() and check that we have
at least received the required amount of data before accessing it. Only
copy the data to that skb that has actually been received.
[mkl: rename gs_usb_get_minimum_length() -> +gs_usb_get_minimum_rx_length()]
Source : NVD
## 5.3
Score
Published December 23, 2025
Severit
Wiz
CVE-2025-68168 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68168 CVE-2025-68168 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68168 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
jfs: fix uninitialized waitqueue in transaction manager
The transaction manager initialization in txInit() was not properly
initializing TxBlock[0].waitor waitqueue, causing a crash when
txEnd(0) is called on read-only filesystems.
When a filesystem is mounted read-only, txBegin() returns tid=0 to
indicate no transaction. However, txEnd(0) still gets called and
tries to access TxBlock[0].waitor via tid_to_tblock(0), but this
waitqueue was never initialized because the initialization loop
started at index 1 instead of 0.
This causes a 'non-static key' lockdep warning and system crash:
INFO: trying to register non-static key in txEnd
Fix by ensurin
Wiz
CVE-2026-23169 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23169 [HIGH] CVE-2026-23169 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23169 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: fix race in mptcp_pm_nl_flush_addrs_doit()
syzbot and Eulgyu Kim reported crashes in mptcp_pm_nl_get_local_id()
and/or mptcp_pm_nl_is_backup()
Root cause is list_splice_init() in mptcp_pm_nl_flush_addrs_doit()
which is not RCU ready.
list_splice_init_rcu() can not be called here while holding pernet->lock
spinlock.
Many thanks to Eulgyu Kim for providing a repro and testing our patches.
Source : NVD
## 4.7
Score
Published February 14, 2026
Severity MEDIUM
CNA Score 7.8
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Pro
Wiz
CVE-2025-68310 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68310 CVE-2025-68310 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68310 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/pci: Avoid deadlock between PCI error recovery and mlx5 crdump
Do not block PCI config accesses through pci_cfg_access_lock() when
executing the s390 variant of PCI error recovery: Acquire just
device_lock() instead of pci_dev_lock() as powerpc's EEH and
generig PCI AER processing do.
During error recovery testing a pair of tasks was reported to be hung:
mlx5_core 0000:00:00.1: mlx5_health_try_recover:338:(pid 5553): health recovery flow aborted, PCI reads still not working
INFO: task kmcheck:72 blocked for more than 122 seconds.
Not tainted 5.14.0-570.12.1.bringup7.el9.s390x #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
Wiz
CVE-2026-23473 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23473 CVE-2026-23473 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23473 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/poll: fix multishot recv missing EOF on wakeup race
When a socket send and shutdown() happen back-to-back, both fire
wake-ups before the receiver's task_work has a chance to run. The first
wake gets poll ownership (poll_refs=1), and the second bumps it to 2.
When io_poll_check_events() runs, it calls io_poll_issue() which does a
recv that reads the data and returns IOU_RETRY. The loop then drains all
accumulated refs (atomic_sub_return(2) -> 0) and exits, even though only
the first event was consumed. Since the shutdown is a persistent state
change, no further wakeups will happen, and the multishot recv can hang
forever.
Check specifically
Wiz
CVE-2022-50700 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50700 CVE-2022-50700 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50700 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath10k: Delay the unmapping of the buffer
On WCN3990, we are seeing a rare scenario where copy engine hardware is
sending a copy complete interrupt to the host driver while still
processing the buffer that the driver has sent, this is leading into an
SMMU fault triggering kernel panic. This is happening on copy engine
channel 3 (CE3) where the driver normally enqueues WMI commands to the
firmware. Upon receiving a copy complete interrupt, host driver will
immediately unmap and frees the buffer presuming that hardware has
processed the buffer. In the issue case, upon receiving copy complete
interrupt, host driver will unmap and free the buffer
Wiz
CVE-2023-54298 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54298 CVE-2023-54298 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54298 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
thermal: intel: quark_dts: fix error pointer dereference
If alloc_soc_dts() fails, then we can just return. Trying to free
"soc_dts" will lead to an Oops.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-kvm
kernel-64k-debug-modules-partner
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW Ha
Wiz
CVE-2022-50749 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50749 CVE-2022-50749 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50749 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
acct: fix potential integer overflow in encode_comp_t()
The integer overflow is descripted with following codes:
317 static comp_t encode_comp_t(u64 value)
318 {
319 int exp, rnd;
......
341 exp <<= MANTSIZE;
342 exp += value;
343 return exp;
344 }
Currently comp_t is defined as type of '__u16', but the variable 'exp' is
type of 'int', so overflow would happen when variable 'exp' in line 343 is
greater than 65535.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perc
Wiz
CVE-2025-71088 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71088 [MEDIUM] CVE-2025-71088 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71088 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: fallback earlier on simult connection
Syzkaller reports a simult-connect race leading to inconsistent fallback
status:
WARNING: CPU: 3 PID: 33 at net/mptcp/subflow.c:1515 subflow_data_ready+0x40b/0x7c0 net/mptcp/subflow.c:1515
Modules linked in:
CPU: 3 UID: 0 PID: 33 Comm: ksoftirqd/3 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:subflow_data_ready+0x40b/0x7c0 net/mptcp/subflow.c:1515
Code: 89 ee e8 78 61 3c f6 40 84 ed 75 21 e8 8e 66 3c f6 44 89 fe bf 07 00 00 00 e8 c1 61 3c f6 41 83 ff 07 74 09 e8 76 66 3c f6 90 0b 90 e8 6d 66 3c f6 48 89
Wiz
CVE-2025-71104 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71104 [MEDIUM] CVE-2025-71104 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71104 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
KVM: x86: Fix VM hard lockup after prolonged inactivity with periodic HV timer
When advancing the target expiration for the guest's APIC timer in periodic
mode, set the expiration to "now" if the target expiration is in the past
(similar to what is done in update_target_expiration()). Blindly adding
the period to the previous target expiration can result in KVM generating
a practically unbounded number of hrtimer IRQs due to programming an
expired timer over and over. In extreme scenarios, e.g. if userspace
pauses/suspends a VM for an extended duration, this can even cause hard
lockups in the host.
Currently, the bug only affects Intel CPUs when us
Wiz
CVE-2025-71077 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71077 [MEDIUM] CVE-2025-71077 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71077 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tpm: Cap the number of PCR banks
tpm2_get_pcr_allocation() does not cap any upper limit for the number of
banks. Cap the limit to eight banks so that out of bounds values coming
from external I/O cause on only limited harm.
Source : NVD
## 5.5
Score
Published January 13, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-mediatek
kernel-default-extra
Sources
NVD
CBL-Mariner 3.0 Severity ME
Wiz
CVE-2026-23475 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23475 CVE-2026-23475 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23475 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: fix statistics allocation
The controller per-cpu statistics is not allocated until after the
controller has been registered with driver core, which leaves a window
where accessing the sysfs attributes can trigger a NULL-pointer
dereference.
Fix this by moving the statistics allocation to controller allocation
while tying its lifetime to that of the controller (rather than using
implicit devres).
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.6
Wiz
CVE-2025-68336 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68336 CVE-2025-68336 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68336 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
locking/spinlock/debug: Fix data-race in do_raw_write_lock
KCSAN reports:
BUG: KCSAN: data-race in do_raw_write_lock / do_raw_write_lock
write (marked) to 0xffff800009cf504c of 4 bytes by task 1102 on cpu 1:
do_raw_write_lock+0x120/0x204
_raw_write_lock_irq
do_exit
call_usermodehelper_exec_async
ret_from_fork
read to 0xffff800009cf504c of 4 bytes by task 1103 on cpu 0:
do_raw_write_lock+0x88/0x204
_raw_write_lock_irq
do_exit
call_usermodehelper_exec_async
ret_from_fork
value changed: 0xffffffff -> 0x00000001
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 1103 Comm: kworker/u4:1 6.1.111
Commit 1a365e822372 ("locking/spinlock/debug: Fi
Wiz
CVE-2023-54207 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2023-54207 [HIGH] CVE-2023-54207 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54207 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
HID: uclogic: Correct devm device reference for hidinput input_dev name
Reference the HID device rather than the input device for the devm
allocation of the input_dev name. Referencing the input_dev would lead to a
use-after-free when the input_dev was unregistered and subsequently fires a
uevent that depends on the name. At the point of firing the uevent, the
name would be freed by devres management.
Use devm_kasprintf to simplify the logic for allocating memory and
formatting the input_dev name string.
Source : NVD
## 7.8
Score
Published December 30, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has P
Wiz
CVE-2025-68757 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68757 CVE-2025-68757 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68757 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/vgem-fence: Fix potential deadlock on release
A timer that expires a vgem fence automatically in 10 seconds is now
released with timer_delete_sync() from fence->ops.release() called on last
dma_fence_put(). In some scenarios, it can run in IRQ context, which is
not safe unless TIMER_IRQSAFE is used. One potentially risky scenario was
demonstrated in Intel DRM CI trybot, BAT run on machine bat-adlp-6, while
working on new IGT subtests syncobj_timeline@stress-* as user space
replacements of some problematic test cases of a dma-fence-chain selftest
[1].
[117.004338] ================================
[117.004340] WARNING: inconsistent lock state
[11
Wiz
CVE-2023-54246 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54246 CVE-2023-54246 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54246 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rcuscale: Move rcu_scale_writer() schedule_timeout_uninterruptible() to _idle()
The rcuscale.holdoff module parameter can be used to delay the start
of rcu_scale_writer() kthread. However, the hung-task timeout will
trigger when the timeout specified by rcuscale.holdoff is greater than
hung_task_timeout_secs:
runqemu kvm nographic slirp qemuparams="-smp 4 -m 2048M"
bootparams="rcuscale.shutdown=0 rcuscale.holdoff=300"
[ 247.071753] INFO: task rcu_scale_write:59 blocked for more than 122 seconds.
[ 247.072529] Not tainted 6.4.0-rc1-00134-gb9ed6de8d4ff #7
[ 247.073400] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 247.0
Wiz
CVE-2025-71185 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71185 [MEDIUM] CVE-2025-71185 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71185 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: ti: dma-crossbar: fix device leak on am335x route allocation
Make sure to drop the reference taken when looking up the crossbar
platform device during am335x route allocation.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-bluefield
linux-oracle
Sources
NVD
Debian 11, 12, 13, 14 Severity MEDIUM Has Fix Added at: Jan 31, 20
Wiz
CVE-2025-71222 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71222 [MEDIUM] CVE-2025-71222 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71222 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: wlcore: ensure skb headroom before skb_push
This avoids occasional skb_under_panic Oops from wl1271_tx_work. In this case, headroom is
less than needed (typically 110 - 94 = 16 bytes).
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-6.14
linux-hwe-6.17
Sources
NVD
CBL-Mariner 3.0 Severity HIGH Has Fix Added at: Mar 13, 2026
Wiz
CVE-2026-23047 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23047 CVE-2026-23047 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23047 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
libceph: make calc_target() set t->paused, not just clear it
Currently calc_target() clears t->paused if the request shouldn't be
paused anymore, but doesn't ever set t->paused even though it's able to
determine when the request should be paused. Setting t->paused is left
to __submit_request() which is fine for regular requests but doesn't
work for linger requests -- since __submit_request() doesn't operate
on linger requests, there is nowhere for lreq->t.paused to be set.
One consequence of this is that watches don't get reestablished on
paused -> unpaused transitions in cases where requests have been paused
long enough for the (paused) unwatch req
Wiz
CVE-2026-23060 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23060 [MEDIUM] CVE-2026-23060 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23060 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: authencesn - reject too-short AAD (assoclen<8) to match ESP/ESN spec
authencesn assumes an ESP/ESN-formatted AAD. When assoclen is shorter than
the minimum expected length, crypto_authenc_esn_decrypt() can advance past
the end of the destination scatterlist and trigger a NULL pointer dereference
in scatterwalk_map_and_copy(), leading to a kernel panic (DoS).
Add a minimum AAD length check to fail fast on invalid inputs.
Source : NVD
## 5.5
Score
Published February 4, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KE
Wiz
CVE-2026-23100 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23100 [MEDIUM] CVE-2026-23100 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23100 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mm/hugetlb: fix hugetlb_pmd_shared()
Patch series "mm/hugetlb: fixes for PMD table sharing (incl. using
mmu_gather)", v3.
One functional fix, one performance regression fix, and two related
comment fixes.
I cleaned up my prototype I recently shared [1] for the performance fix,
deferring most of the cleanups I had in the prototype to a later point.
While doing that I identified the other things.
The goal of this patch set is to be backported to stable trees "fairly"
easily. At least patch #1 and #4.
Patch #1 fixes hugetlb_pmd_shared() not detecting any sharing
Patch #2 + #3 are simple comment fixes that patch #4 interacts with.
Patch #4 is a fix
Wiz
CVE-2022-50697 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50697 CVE-2022-50697 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50697 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mrp: introduce active flags to prevent UAF when applicant uninit
The caller of del_timer_sync must prevent restarting of the timer, If
we have no this synchronization, there is a small probability that the
cancellation will not be successful.
## And syzbot report the fellowing crash:
BUG: KASAN: use-after-free in hlist_add_head include/linux/list.h:929 [inline]
BUG: KASAN: use-after-free in enqueue_timer+0x18/0xa4 kernel/time/timer.c:605
Write at addr f9ff000024df6058 by task syz-fuzzer/2256
Pointer tag: [f9], memory tag: [fe]
CPU: 1 PID: 2256 Comm: syz-fuzzer Not tainted 6.1.0-rc5-syzkaller-00008-
ge01d50cbd6ee #0
Hardware name: linux,dummy-vi
Wiz
CVE-2025-68289 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68289 CVE-2025-68289 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68289 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: gadget: f_eem: Fix memory leak in eem_unwrap
The existing code did not handle the failure case of usb_ep_queue in the
command path, potentially leading to memory leaks.
Improve error handling to free all allocated resources on usb_ep_queue
failure. This patch continues to use goto logic for error handling, as the
existing error handling is complex and not easily adaptable to auto-cleanup
helpers.
kmemleak results:
unreferenced object 0xffffff895a512300 (size 240):
backtrace:
slab_post_alloc_hook+0xbc/0x3a4
kmem_cache_alloc+0x1b4/0x358
skb_clone+0x90/0xd8
eem_unwrap+0x1cc/0x36c
unreferenced object 0xffffff8a157f4000 (size 256):
backtrace:
slab
Wiz
CVE-2026-31406 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-31406 CVE-2026-31406 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31406 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_keepalive_work);
rcu_bar
Wiz
CVE-2025-71076 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71076 [MEDIUM] CVE-2025-71076 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71076 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/oa: Limit num_syncs to prevent oversized allocations
The OA open parameters did not validate num_syncs, allowing
userspace to pass arbitrarily large values, potentially
leading to excessive allocations.
Add check to ensure that num_syncs does not exceed DRM_XE_MAX_SYNCS,
returning -EINVAL when the limit is violated.
v2: use XE_IOCTL_DBG() and drop duplicated check. (Ashutosh)
(cherry picked from commit e057b2d2b8d815df3858a87dffafa2af37e5945b)
Source : NVD
## 5.5
Score
Published January 13, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV
Wiz
CVE-2022-50816 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50816 CVE-2022-50816 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50816 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipv6: ensure sane device mtu in tunnels
Another syzbot report [1] with no reproducer hints
at a bug in ip6_gre tunnel (dev:ip6gretap0)
Since ipv6 mcast code makes sure to read dev->mtu once
and applies a sanity check on it (see commit b9b312a7a451
"ipv6: mcast: better catch silly mtu values"), a remaining
possibility is that a layer is able to set dev->mtu to
an underflowed value (high order bit set).
This could happen indeed in ip6gre_tnl_link_config_route(),
ip6_tnl_link_config() and ipip6_tunnel_bind_dev()
Make sure to sanitize mtu value in a local variable before
it is written once on dev->mtu, as lockless readers could
catch wrong temporary
Wiz
CVE-2026-23376 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23376 CVE-2026-23376 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23376 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvmet-fcloop: Check remoteport port_state before calling done callback
In nvme_fc_handle_ls_rqst_work, the lsrsp->done callback is only set when
remoteport->port_state is FC_OBJSTATE_ONLINE. Otherwise, the
nvme_fc_xmt_ls_rsp's LLDD call to lport->ops->xmt_ls_rsp is expected to
fail and the nvme-fc transport layer itself will directly call
nvme_fc_xmt_ls_rsp_free instead of relying on LLDD's done callback to free
the lsrsp resources.
Update the fcloop_t2h_xmt_ls_rsp routine to check remoteport->port_state.
If online, then lsrsp->done callback will free the lsrsp. Else, return
-ENODEV to signal the nvme-fc transport to handle freeing lsrsp.
Source :
Wiz
CVE-2023-54244 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54244 CVE-2023-54244 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54244 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ACPI: EC: Fix oops when removing custom query handlers
When removing custom query handlers, the handler might still
be used inside the EC query workqueue, causing a kernel oops
if the module holding the callback function was already unloaded.
Fix this by flushing the EC query workqueue when removing
custom query handlers.
Tested on a Acer Travelmate 4002WLMi
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Af
Wiz
CVE-2023-53998 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53998 CVE-2023-53998 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53998 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hwrng: virtio - Fix race on data_avail and actual data
The virtio rng device kicks off a new entropy request whenever the
data available reaches zero. When a new request occurs at the end
of a read operation, that is, when the result of that request is
only needed by the next reader, then there is a race between the
writing of the new data and the next reader.
This is because there is no synchronisation whatsoever between the
writer and the reader.
Fix this by writing data_avail with smp_store_release and reading
it with smp_load_acquire when we first enter read. The subsequent
reads are safe because they're either protected by the first load
acqu
Wiz
CVE-2023-54117 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54117 CVE-2023-54117 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54117 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/dcssblk: fix kernel crash with list_add corruption
Commit fb08a1908cb1 ("dax: simplify the dax_device gendisk
association") introduced new logic for gendisk association, requiring
drivers to explicitly call dax_add_host() and dax_remove_host().
For dcssblk driver, some dax_remove_host() calls were missing, e.g. in
device remove path. The commit also broke error handling for out_dax case
in device add path, resulting in an extra put_device() w/o the previous
get_device() in that case.
This lead to stale xarray entries after device add / remove cycles. In the
case when a previously used struct gendisk pointer (xarray index) would be
used again,
Wiz
CVE-2023-54198 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54198 CVE-2023-54198 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54198 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tty: fix out-of-bounds access in tty_driver_lookup_tty()
When specifying an invalid console= device like console=tty3270,
tty_driver_lookup_tty() returns the tty struct without checking
whether index is a valid number.
To reproduce:
qemu-system-x86_64 -enable-kvm -nographic -serial mon:stdio
-kernel ../linux-build-x86/arch/x86/boot/bzImage
-append "console=ttyS0 console=tty3270"
This crashes with:
[ 0.770599] BUG: kernel NULL pointer dereference, address: 00000000000000ef
[ 0.771265] #PF: supervisor read access in kernel mode
[ 0.771773] #PF: error_code(0x0000) - not-present page
[ 0.772609] Oops: 0000 [#1] PREEMPT SMP PTI
[ 0.774878] RIP: 0010:
Wiz
CVE-2023-54085 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54085 CVE-2023-54085 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54085 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: fix NULL pointer dereference on fastopen early fallback
In case of early fallback to TCP, subflow_syn_recv_sock() deletes
the subflow context before returning the newly allocated sock to
the caller.
The fastopen path does not cope with the above unconditionally
dereferencing the subflow context.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-interna
Wiz
CVE-2026-23307 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23307 CVE-2026-23307 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23307 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message
When looking at the data in a USB urb, the actual_length is the size of
the buffer passed to the driver, not the transfer_buffer_length which is
set by the driver as the max size of the buffer.
When parsing the messages in ems_usb_read_bulk_callback() properly check
the size both at the beginning of parsing the message to make sure it is
big enough for the expected structure, and at the end of the message to
make sure we don't overflow past the end of the buffer for the next
message.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N
Wiz
CVE-2026-23243 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23243 [HIGH] CVE-2026-23243 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23243 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/umad: Reject negative data_len in ib_umad_write
ib_umad_write computes data_len from user-controlled count and the
MAD header sizes. With a mismatched user MAD header size and RMPP
header length, data_len can become negative and reach ib_create_send_mad().
This can make the padding calculation exceed the segment size and trigger
an out-of-bounds memset in alloc_send_rmpp_list().
Add an explicit check to reject negative data_len before creating the
send buffer.
KASAN splat:
[ 211.363464] BUG: KASAN: slab-out-of-bounds in ib_create_send_mad+0xa01/0x11b0
[ 211.364077] Write of size 220 at addr ffff88800c3fa1f8 by task spray_thread/102
[ 211.3658
Wiz
CVE-2022-50853 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50853 CVE-2022-50853 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50853 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFSv4: Fix a credential leak in _nfs4_discover_trunking()
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-abi-whitelists
kernel-core
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 6, 8, 9 Severity MEDIUM No Fix Added at: Dec 31, 2025
Ubuntu 16.04, 18.04 Severity MEDIUM No Fix Added at: Jan 02, 2026
Ubuntu
Wiz
CVE-2023-54186 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54186 CVE-2023-54186 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54186 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: typec: altmodes/displayport: fix pin_assignment_show
This patch fixes negative indexing of buf array in pin_assignment_show
when get_current_pin_assignments returns 0 i.e. no compatible pin
assignments are found.
BUG: KASAN: use-after-free in pin_assignment_show+0x26c/0x33c
...
Call trace:
dump_backtrace+0x110/0x204
dump_stack_lvl+0x84/0xbc
print_report+0x358/0x974
kasan_report+0x9c/0xfc
__do_kernel_fault+0xd4/0x2d4
do_bad_area+0x48/0x168
do_tag_check_fault+0x24/0x38
do_mem_abort+0x6c/0x14c
el1_abort+0x44/0x68
el1h_64_sync_handler+0x64/0xa4
el1h_64_sync+0x78/0x7c
pin_assignment_show+0x26c/0x33c
dev_attr_show+0x50/0xc0
Source : NVD
Published
Wiz
CVE-2026-23220 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23220 [MEDIUM] CVE-2026-23220 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23220 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix infinite loop caused by next_smb2_rcv_hdr_off reset in error paths
The problem occurs when a signed request fails smb2 signature verification
check. In __process_request(), if check_sign_req() returns an error,
set_smb2_rsp_status(work, STATUS_ACCESS_DENIED) is called.
set_smb2_rsp_status() set work->next_smb2_rcv_hdr_off as zero. By resetting
next_smb2_rcv_hdr_off to zero, the pointer to the next command in the chain
is lost. Consequently, is_chained_smb2_message() continues to point to
the same request header instead of advancing. If the header's NextCommand
field is non-zero, the function returns true, causing __handle_ksmbd_work()
to
Wiz
CVE-2026-23191 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23191 [HIGH] CVE-2026-23191 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23191 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ALSA: aloop: Fix racy access at PCM trigger
The PCM trigger callback of aloop driver tries to check the PCM state
and stop the stream of the tied substream in the corresponding cable.
Since both check and stop operations are performed outside the cable
lock, this may result in UAF when a program attempts to trigger
frequently while opening/closing the tied stream, as spotted by
fuzzers.
For addressing the UAF, this patch changes two things:
It covers the most of code in loopback_check_format() with
cable->lock spinlock, and add the proper NULL checks. This avoids
already some racy accesses.
In addition, now we try to check the state of the captur
Wiz
CVE-2026-23471 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23471 CVE-2026-23471 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23471 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm: Fix use-after-free on framebuffers and property blobs when calling drm_dev_unplug
When trying to do a rather aggressive test of igt's "xe_module_load
--r reload" with a full desktop environment and game running I noticed
a few OOPSes when dereferencing freed pointers, related to
framebuffers and property blobs after the compositor exits.
Solve this by guarding the freeing in drm_file with drm_dev_enter/exit,
and immediately put the references from struct drm_file objects during
drm_dev_unplug().
Related warnings for framebuffers on the subtest:
[ 739.713076] ------------[ cut here ]------------
WARN_ON(!list_empty(&dev->mode_config.fb_list))
Wiz
CVE-2026-23300 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23300 CVE-2026-23300 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23300 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop
When a standalone IPv6 nexthop object is created with a loopback device
(e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies
it as a reject route. This is because nexthop objects have no destination
prefix (fc_dst=::), causing fib6_is_reject() to match any loopback
nexthop. The reject path skips fib_nh_common_init(), leaving
nhc_pcpu_rth_output unallocated. If an IPv4 route later references this
nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and
panics.
Simplify the check in fib6_nh_init() to only match explicit reject
routes (RTF_REJECT) ins
Wiz
CVE-2022-50720 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50720 CVE-2022-50720 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50720 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/apic: Don't disable x2APIC if locked
The APIC supports two modes, legacy APIC (or xAPIC), and Extended APIC
(or x2APIC). X2APIC mode is mostly compatible with legacy APIC, but
it disables the memory-mapped APIC interface in favor of one that uses
MSRs. The APIC mode is controlled by the EXT bit in the APIC MSR.
The MMIO/xAPIC interface has some problems, most notably the APIC LEAK 1 . This bug allows an attacker to use the APIC MMIO interface to
extract data from the SGX enclave.
Introduce support for a new feature that will allow the BIOS to lock
the APIC in x2APIC mode. If the APIC is locked in x2APIC mode and the
kernel tries to disable the
Wiz
CVE-2025-68202 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68202 CVE-2025-68202 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68202 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
sched_ext: Fix unsafe locking in the scx_dump_state()
For built with CONFIG_PREEMPT_RT=y kernels, the dump_lock will be converted
sleepable spinlock and not disable-irq, so the following scenarios occur:
inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
irq_work/0/27 [HC0[0]:SC0[0]:HE1:SE1] takes:
(&rq->__lock){?...}-{2:2}, at: raw_spin_rq_lock_nested+0x2b/0x40
{IN-HARDIRQ-W} state was registered at:
lock_acquire+0x1e1/0x510
_raw_spin_lock_nested+0x42/0x80
raw_spin_rq_lock_nested+0x2b/0x40
sched_tick+0xae/0x7b0
update_process_times+0x14c/0x1b0
tick_periodic+0x62/0x1f0
tick_handle_periodic+0x48/0xf0
timer_interrupt+0x55/0x80
__handle_irq_event_pe
Wiz
CVE-2025-68752 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68752 CVE-2025-68752 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68752 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iavf: Implement settime64 with -EOPNOTSUPP
ptp_clock_settime() assumes every ptp_clock has implemented settime64().
Stub it with -EOPNOTSUPP to prevent a NULL dereference.
The fix is similar to commit 329d050bbe63 ("gve: Implement settime64
with -EOPNOTSUPP").
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-cross-headers
kernel
Sources
NVD
Debian 14 Has Fix Added at:
Wiz
CVE-2026-23137 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23137 [MEDIUM] CVE-2026-23137 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23137 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
of: unittest: Fix memory leak in unittest_data_add()
In unittest_data_add(), if of_resolve_phandles() fails, the allocated
unittest_data is not freed, leading to a memory leak.
Fix this by using scope-based cleanup helper __free(kfree) for automatic
resource cleanup. This ensures unittest_data is automatically freed when
it goes out of scope in error paths.
For the success path, use retain_and_null_ptr() to transfer ownership
of the memory to the device tree and prevent double freeing.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit N
Wiz
CVE-2026-22980 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-22980 [HIGH] CVE-2026-22980 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22980 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfsd: provide locking for v4_end_grace
Writing to v4_end_grace can race with server shutdown and result in
memory being accessed after it was freed - reclaim_str_hashtbl in
particularly.
We cannot hold nfsd_mutex across the nfsd4_end_grace() call as that is
held while client_tracking_op->init() is called and that can wait for
an upcall to nfsdcltrack which can write to v4_end_grace, resulting in a
deadlock.
nfsd4_end_grace() is also called by the landromat work queue and this
doesn't require locking as server shutdown will stop the work and wait
for it before freeing anything that nfsd4_end_grace() might access.
However, we must be sure that writ
Wiz
CVE-2025-68807 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68807 CVE-2025-68807 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68807 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: fix race between wbt_enable_default and IO submission
When wbt_enable_default() is moved out of queue freezing in elevator_change(),
it can cause the wbt inflight counter to become negative (-1), leading to hung
tasks in the writeback path. Tasks get stuck in wbt_wait() because the counter
is in an inconsistent state.
The issue occurs because wbt_enable_default() could race with IO submission,
allowing the counter to be decremented before proper initialization. This manifests
as:
rq_wait[0]:
inflight: -1
has_waiters: True
rwb_enabled() checks the state, which can be updated exactly between wbt_wait()
(rq_qos_throttle()) and wbt_track()(rq_
Wiz
CVE-2023-54006 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54006 CVE-2023-54006 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54006 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
af_unix: Fix data-race around unix_tot_inflight.
unix_tot_inflight is changed under spin_lock(unix_gc_lock), but
unix_release_sock() reads it locklessly.
Let's use READ_ONCE() for unix_tot_inflight.
Note that the writer side was marked by commit 9d6d7f1cb67c ("af_unix:
annote lockless accesses to unix_tot_inflight & gc_in_progress")
BUG: KCSAN: data-race in unix_inflight / unix_release_sock
write (marked) to 0xffffffff871852b8 of 4 bytes by task 123 on cpu 1:
unix_inflight+0x130/0x180 net/unix/scm.c:64
unix_attach_fds+0x137/0x1b0 net/unix/scm.c:123
unix_scm_to_skb net/unix/af_unix.c:1832 [inline]
unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.
Wiz
CVE-2026-23083 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23083 [HIGH] CVE-2026-23083 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23083 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fou: Don't allow 0 for FOU_ATTR_IPPROTO.
fou_udp_recv() has the same problem mentioned in the previous
patch.
If FOU_ATTR_IPPROTO is set to 0, skb is not freed by
fou_udp_recv() nor "resubmit"-ted in ip_protocol_deliver_rcu().
Let's forbid 0 for FOU_ATTR_IPPROTO.
Source : NVD
## 7.8
Score
Published February 4, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg
kernel6.12-libbpf
Wiz
CVE-2026-23180 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.0
CVE-2026-23180 [HIGH] CVE-2026-23180 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23180 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dpaa2-switch: add bounds check for if_id in IRQ handler
The IRQ handler extracts if_id from the upper 16 bits of the hardware
status register and uses it to index into ethsw->ports[] without
validation. Since if_id can be any 16-bit value (0-65535) but the ports
array is only allocated with sw_attr.num_ifs elements, this can lead to
an out-of-bounds read potentially.
Add a bounds check before accessing the array, consistent with the
existing validation in dpaa2_switch_rx().
Source : NVD
## 7
Score
Published February 14, 2026
Severity HIGH
CNA Score 7.0
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Ex
Wiz
CVE-2026-23301 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23301 CVE-2026-23301 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23301 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: SDCA: Add allocation failure check for Entity name
Currently find_sdca_entity_iot() can allocate a string for the
Entity name but it doesn't check if that allocation succeeded.
Add the missing NULL check after the allocation.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-modules
kernel-64k-debug-modules-core
Sources
NVD
Debian 14 Has Fix Added at: Mar
Wiz
CVE-2025-40338 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40338 CVE-2025-40338 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40338 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: Intel: avs: Do not share the name pointer between components
By sharing 'name' directly, tearing down components may lead to
use-after-free errors. Duplicate the name to avoid that.
At the same time, update the order of operations - since commit
cee28113db17 ("ASoC: dmaengine_pcm: Allow passing component name via
config") the framework does not override component->name if set before
invoking the initializer.
Source : NVD
## 6.4
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/
Wiz
CVE-2023-54315 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54315 CVE-2023-54315 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54315 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
powerpc/powernv/sriov: perform null check on iov before dereferencing iov
Currently pointer iov is being dereferenced before the null check of iov
which can lead to null pointer dereference errors. Fix this by moving the
iov null check before the dereferencing.
Detected using cppcheck static analysis:
linux/arch/powerpc/platforms/powernv/pci-sriov.c:597:12: warning: Either
the condition '!iov' is redundant or there is possible null pointer
dereference: iov. [nullPointerRedundantCheck]
num_vfs = iov->num_vfs;
^
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CIS
Wiz
CVE-2022-50839 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50839 CVE-2022-50839 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50839 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
jbd2: fix potential buffer head reference count leak
As in 'jbd2_fc_wait_bufs' if buffer isn't uptodate, will return -EIO without
update 'journal->j_fc_off'. But 'jbd2_fc_release_bufs' will release buffer head
from ‘j_fc_off - 1’ if 'bh' is NULL will terminal release which will lead to
buffer head buffer head reference count leak.
To solve above issue, update 'journal->j_fc_off' before return -EIO.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Wiz
CVE-2026-23388 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23388 CVE-2026-23388 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23388 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Squashfs: check metadata block offset is within range
Syzkaller reports a "general protection fault in squashfs_copy_data"
This is ultimately caused by a corrupted index look-up table, which
produces a negative metadata block offset.
This is subsequently passed to squashfs_copy_data (via
squashfs_read_metadata) where the negative offset causes an out of bounds
access.
The fix is to check that the offset is within range in
squashfs_read_metadata. This will trap this and other cases.
Source : NVD
## 6.3
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has
Wiz
CVE-2023-54134 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54134 CVE-2023-54134 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54134 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
autofs: fix memory leak of waitqueues in autofs_catatonic_mode
Syzkaller reports a memory leak:
BUG: memory leak
unreferenced object 0xffff88810b279e00 (size 96):
comm "syz-executor399", pid 3631, jiffies 4294964921 (age 23.870s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 08 9e 27 0b 81 88 ff ff ..........'.....
08 9e 27 0b 81 88 ff ff 00 00 00 00 00 00 00 00 ..'.............
backtrace:
[ ] kmalloc_trace+0x20/0x90 mm/slab_common.c:1046
[ ] kmalloc include/linux/slab.h:576 [inline]
[ ] autofs_wait+0x3fa/0x9a0 fs/autofs/waitq.c:378
[ ] autofs_do_expire_multi+0xa7/0x3e0 fs/autofs/expire.c:593
[ ] autofs_expire_multi+0x53/0x80 fs/autofs/expire.
Wiz
CVE-2025-68789 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68789 CVE-2025-68789 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68789 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-xilinx
kernel-rt-core
Sources
NVD
Debian 11 No Fix Added at: Jan 14, 2026
Debian 12, 13, 14 Has Fix Added at: Jan 14, 2026
Echo Has Fix Added at: Jan 14, 2026
Red Hat 6, 7, 8, 9, 10 Severity LOW No Fix Added at: Jan 15, 2026
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Jan 15, 202
Wiz
CVE-2023-54108 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54108 CVE-2023-54108 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54108 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qla2xxx: Fix DMA-API call trace on NVMe LS requests
The following message and call trace was seen with debug kernels:
DMA-API: qla2xxx 0000:41:00.0: device driver failed to check map
error [device address=0x00000002a3ff38d8] [size=1024 bytes] [mapped as
single]
WARNING: CPU: 0 PID: 2930 at kernel/dma/debug.c:1017
check_unmap+0xf42/0x1990
Call Trace:
debug_dma_unmap_page+0xc9/0x100
qla_nvme_ls_unmap+0x141/0x210 [qla2xxx]
Remove DMA mapping from the driver altogether, as it is already done by FC
layer. This prevents the warning.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has P
Wiz
CVE-2026-23106 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23106 [MEDIUM] CVE-2026-23106 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23106 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
timekeeping: Adjust the leap state for the correct auxiliary timekeeper
When __do_ajdtimex() was introduced to handle adjtimex for any
timekeeper, this reference to tk_core was not updated. When called on an
auxiliary timekeeper, the core timekeeper would be updated incorrectly.
This gets caught by the lock debugging diagnostics because the
timekeepers sequence lock gets written to without holding its
associated spinlock:
WARNING: include/linux/seqlock.h:226 at __do_adjtimex+0x394/0x3b0, CPU#2: test/125
aux_clock_adj (kernel/time/timekeeping.c:2979)
__do_sys_clock_adjtime (kernel/time/posix-timers.c:1161 kernel/time/posix-timers.c:1173)
do_syscall
Wiz
CVE-2022-50848 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50848 CVE-2022-50848 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50848 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drivers: dio: fix possible memory leak in dio_init()
If device_register() returns error, the 'dev' and name needs be
freed. Add a release function, and then call put_device() in the
error path, so the name is freed in kobject_cleanup() and to the
'dev' is freed in release function.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg-5.15
ocfs2-kmp-default
Sourc
Wiz
CVE-2026-23394 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23394 CVE-2026-23394 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23394 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
af_unix: Give up GC if MSG_PEEK intervened.
Igor Ushakov reported that GC purged the receive queue of
an alive socket due to a race with MSG_PEEK with a nice repro.
This is the exact same issue previously fixed by commit
cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK").
After GC was replaced with the current algorithm, the cited
commit removed the locking dance in unix_peek_fds() and
reintroduced the same issue.
The problem is that MSG_PEEK bumps a file refcount without
interacting with GC.
Consider an SCC containing sk-A and sk-B, where sk-A is
close()d but can be recv()ed via sk-B.
The bad thing happens if sk-A is recv()ed with MSG_P
Wiz
CVE-2023-54178 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54178 CVE-2023-54178 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54178 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
of: unittest: fix null pointer dereferencing in of_unittest_find_node_by_name()
when kmalloc() fail to allocate memory in kasprintf(), name
or full_name will be NULL, strcmp() will cause
null pointer dereference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 20.3
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
dtb-xilinx
kernel-64kb-devel
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added
Wiz
CVE-2026-23068 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23068 [HIGH] CVE-2026-23068 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23068 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
spi: spi-sprd-adi: Fix double free in probe error path
The driver currently uses spi_alloc_host() to allocate the controller
but registers it using devm_spi_register_controller().
If devm_register_restart_handler() fails, the code jumps to the
put_ctlr label and calls spi_controller_put(). However, since the
controller was registered via a devm function, the device core will
automatically call spi_controller_put() again when the probe fails.
This results in a double-free of the spi_controller structure.
Fix this by switching to devm_spi_alloc_host() and removing the
manual spi_controller_put() call.
Source : NVD
## 7.8
Score
Published Februa
Wiz
CVE-2025-68782 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68782 CVE-2025-68782 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68782 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: target: Reset t_task_cdb pointer in error case
If allocation of cmd->t_task_cdb fails, it remains NULL but is later
dereferenced in the 'err' path.
In case of error, reset NULL t_task_cdb value to point at the default
fixed-size buffer.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
kernel-debug-modules-
Wiz
CVE-2026-23315 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23315 CVE-2026-23315 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23315 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211()
Check frame length before accessing the mgmt fields in
mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob
access.
[fix check to also cover mgmt->u.action.u.addba_req.capab,
correct Fixes tag]
Source : NVD
## 7.1
Score
Published March 25, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-de
Wiz
CVE-2023-54007 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54007 CVE-2023-54007 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54007 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
vmci_host: fix a race condition in vmci_host_poll() causing GPF
During fuzzing, a general protection fault is observed in
vmci_host_poll().
general protection fault, probably for non-canonical address 0xdffffc0000000019: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000000c8-0x00000000000000cf]
RIP: 0010:__lock_acquire+0xf3/0x5e00 kernel/locking/lockdep.c:4926
Call Trace: lock_acquire+0x1a4/0x4a0 kernel/locking/lockdep.c:5672
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0xb3/0x100 kernel/locking/spinlock.c:162
add_wait_queue+0x3d/0x260 kernel/sched/wait.c:22
poll_wait include/
Wiz
CVE-2026-23066 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23066 [HIGH] CVE-2026-23066 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23066 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rxrpc: Fix recvmsg() unconditional requeue
If rxrpc_recvmsg() fails because MSG_DONTWAIT was specified but the call at
the front of the recvmsg queue already has its mutex locked, it requeues
the call - whether or not the call is already queued. The call may be on
the queue because MSG_PEEK was also passed and so the call was not dequeued
or because the I/O thread requeued it.
The unconditional requeue may then corrupt the recvmsg queue, leading to
things like UAFs or refcount underruns.
Fix this by only requeuing the call if it isn't already on the queue - and
moving it to the front if it is already queued. If we don't queue it, we
have to put th
Wiz
CVE-2022-50826 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50826 CVE-2022-50826 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50826 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipu3-imgu: Fix NULL pointer dereference in imgu_subdev_set_selection()
Calling v4l2_subdev_get_try_crop() and v4l2_subdev_get_try_compose()
with a subdev state of NULL leads to a NULL pointer dereference. This
can currently happen in imgu_subdev_set_selection() when the state
passed in is NULL, as this method first gets pointers to both the "try"
and "active" states and only then decides which to use.
The same issue has been addressed for imgu_subdev_get_selection() with
commit 30d03a0de650 ("ipu3-imgu: Fix NULL pointer dereference in active
selection access"). However the issue still persists in
imgu_subdev_set_selection().
Therefore, apply a sim
Wiz
CVE-2025-68184 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68184 CVE-2025-68184 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68184 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/mediatek: Disable AFBC support on Mediatek DRM driver
Commit c410fa9b07c3 ("drm/mediatek: Add AFBC support to Mediatek DRM
driver") added AFBC support to Mediatek DRM and enabled the
32x8/split/sparse modifier.
However, this is currently broken on Mediatek MT8188 (Genio 700 EVK
platform); tested using upstream Kernel and Mesa (v25.2.1), AFBC is used by
default since Mesa v25.0.
Kernel trace reports vblank timeouts constantly, and the render is garbled:
[CRTC:62:crtc-0] vblank wait timed out
WARNING: CPU: 7 PID: 70 at drivers/gpu/drm/drm_atomic_helper.c:1835 drm_atomic_helper_wait_for_vblanks.part.0+0x24c/0x27c
[...]
Hardware name: MediaTek Ge
Wiz
CVE-2025-71153 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71153 [MEDIUM] CVE-2025-71153 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71153 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ksmbd: Fix memory leak in get_file_all_info()
In get_file_all_info(), if vfs_getattr() fails, the function returns
immediately without freeing the allocated filename, leading to a memory
leak.
Fix this by freeing the filename before returning in this error case.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-tools-libs
kernel-debug-mo
Wiz
CVE-2023-54101 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54101 CVE-2023-54101 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54101 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
driver: soc: xilinx: use _safe loop iterator to avoid a use after free
The hash_for_each_possible() loop dereferences "eve_data" to get the
next item on the list. However the loop frees eve_data so it leads to
a use after free. Use hash_for_each_possible_safe() instead.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-devel
reiserfs-kmp-64kb
Sources
NVD
Debian 12, 13
Wiz
CVE-2026-23363 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23363 CVE-2026-23363 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23363 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7925: Fix possible oob access in mt7925_mac_write_txwi_80211()
Check frame length before accessing the mgmt fields in
mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug
kernel-64k-debug-modules-internal
Sources
NVD
Debian 13 No Fix Added at: Mar 26, 2026
Debian 14 Has Fix Added a
Wiz
CVE-2026-23206 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23206 [MEDIUM] CVE-2026-23206 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23206 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dpaa2-switch: prevent ZERO_SIZE_PTR dereference when num_ifs is zero
The driver allocates arrays for ports, FDBs, and filter blocks using
kcalloc() with ethsw->sw_attr.num_ifs as the element count. When the
device reports zero interfaces (either due to hardware configuration
or firmware issues), kcalloc(0, ...) returns ZERO_SIZE_PTR (0x10)
instead of NULL.
Later in dpaa2_switch_probe(), the NAPI initialization unconditionally
accesses ethsw->ports[0]->netdev, which attempts to dereference
ZERO_SIZE_PTR (address 0x10), resulting in a kernel panic.
Add a check to ensure num_ifs is greater than zero after retrieving
device attributes. This prevents t
Wiz
CVE-2026-23038 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23038 CVE-2026-23038 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23038 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pnfs/flexfiles: Fix memory leak in nfs4_ff_alloc_deviceid_node()
In nfs4_ff_alloc_deviceid_node(), if the allocation for ds_versions fails,
the function jumps to the out_scratch label without freeing the already
allocated dsaddrs list, leading to a memory leak.
Fix this by jumping to the out_err_drain_dsaddrs label, which properly
frees the dsaddrs list before cleaning up other resources.
Source : NVD
Published January 31, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.1
Exploitati
Wiz
CVE-2025-68379 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68379 CVE-2025-68379 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68379 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/rxe: Fix null deref on srq->rq.queue after resize failure
A NULL pointer dereference can occur in rxe_srq_chk_attr() when
ibv_modify_srq() is invoked twice in succession under certain error
conditions. The first call may fail in rxe_queue_resize(), which leads
rxe_srq_from_attr() to set srq->rq.queue = NULL. The second call then
triggers a crash (null deref) when accessing
srq->rq.queue->buf->index_mask.
Call Trace: rxe_modify_srq+0x170/0x480 [rdma_rxe]
? __pfx_rxe_modify_srq+0x10/0x10 [rdma_rxe]
? uverbs_try_lock_object+0x4f/0xa0 [ib_uverbs]
? rdma_lookup_get_uobject+0x1f0/0x380 [ib_uverbs]
ib_uverbs_modify_srq+0x204/0x290 [ib_uverbs]
? __pfx
Wiz
CVE-2023-54064 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54064 CVE-2023-54064 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54064 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipmi:ssif: Fix a memory leak when scanning for an adapter
The adapter scan ssif_info_find() sets info->adapter_name if the adapter
info came from SMBIOS, as it's not set in that case. However, this
function can be called more than once, and it will leak the adapter name
if it had already been set. So check for NULL before setting it.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libra
Wiz
CVE-2026-22981 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22981 [MEDIUM] CVE-2026-22981 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22981 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
idpf: detach and close netdevs while handling a reset
Protect the reset path from callbacks by setting the netdevs to detached
state and close any netdevs in UP state until the reset handling has
completed. During a reset, the driver will de-allocate resources for the
vport, and there is no guarantee that those will recover, which is why the
existing vport_ctrl_lock does not provide sufficient protection.
idpf_detach_and_close() is called right before reset handling. If the
reset handling succeeds, the netdevs state is recovered via call to
idpf_attach_and_open(). If the reset handling fails the netdevs remain
down. The detach/down calls are protec
Wiz
CVE-2026-31788 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 8.2
CVE-2026-31788 [HIGH] CVE-2026-31788 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-31788 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xen/privcmd: restrict usage in unprivileged domU
The Xen privcmd driver allows to issue arbitrary hypercalls from
user space processes. This is normally no problem, as access is
usually limited to root and the hypervisor will deny any hypercalls
affecting other domains.
In case the guest is booted using secure boot, however, the privcmd
driver would be enabling a root user process to modify e.g. kernel
memory contents, thus breaking the secure boot feature.
The only known case where an unprivileged domU is really needing to
use the privcmd driver is the case when it is acting as the device
model for another guest. In this case all hypercalls issue
Wiz
CVE-2022-50858 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50858 CVE-2022-50858 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50858 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mmc: alcor: fix return value check of mmc_add_host()
mmc_add_host() may return error, if we ignore its return value, the memory
that allocated in mmc_alloc_host() will be leaked and it will lead a kernel
crash because of deleting not added device in the remove path.
So fix this by checking the return value and calling mmc_free_host() in the
error path.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affecte
Wiz
CVE-2023-54175 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54175 CVE-2023-54175 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54175 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i2c: xiic: xiic_xfer(): Fix runtime PM leak on error path
The xiic_xfer() function gets a runtime PM reference when the function is
entered. This reference is released when the function is exited. There is
currently one error path where the function exits directly, which leads to
a leak of the runtime PM reference.
Make sure that this error path also releases the runtime PM reference.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitatio
Wiz
CVE-2026-23055 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23055 CVE-2026-23055 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23055 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i2c: riic: Move suspend handling to NOIRQ phase
Commit 53326135d0e0 ("i2c: riic: Add suspend/resume support") added
suspend support for the Renesas I2C driver and following this change
on RZ/G3E the following WARNING is seen on entering suspend ...
[ 134.275704] Freezing remaining freezable tasks completed (elapsed 0.001 seconds)
[ 134.285536] ------------[ cut here ]------------
[ 134.290298] i2c i2c-2: Transfer while suspended
[ 134.295174] WARNING: drivers/i2c/i2c-core.h:56 at __i2c_smbus_xfer+0x1e4/0x214, CPU#0: systemd-sleep/388
[ 134.365507] Tainted: [W]=WARN
[ 134.368485] Hardware name: Renesas SMARC EVK version 2 based on r9a09g047e57 (DT)
Wiz
CVE-2023-54320 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54320 CVE-2023-54320 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54320 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86/amd: pmc: Fix memory leak in amd_pmc_stb_debugfs_open_v2()
Function amd_pmc_stb_debugfs_open_v2() may be called when the STB
debug mechanism enabled.
When amd_pmc_send_cmd() fails, the 'buf' needs to be released.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-gke
linux-intel-iotg
Sources
NVD
Debian 11, 12 No Fix Added at: Dec 31, 2025
Debian 13, 14 Ha
Wiz
CVE-2023-53828 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53828 CVE-2023-53828 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53828 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_add_adv_monitor()
KSAN reports use-after-free in hci_add_adv_monitor().
While adding an adv monitor,
hci_add_adv_monitor() calls ->
msft_add_monitor_pattern() calls ->
msft_add_monitor_sync() calls ->
msft_le_monitor_advertisement_cb() calls in an error case ->
hci_free_adv_monitor() which frees the *moniter.
This is referenced by bt_dev_dbg() in hci_add_adv_monitor().
Fix the bt_dev_dbg() by using handle instead of monitor->handle.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CIS
Wiz
CVE-2022-50887 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50887 CVE-2022-50887 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50887 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
regulator: core: fix unbalanced of node refcount in regulator_dev_lookup()
I got the the following report:
OF: ERROR: memory leak, expected refcount 1 instead of 2,
of_node_get()/of_node_put() unbalanced - destroy cset entry:
attach overlay node /i2c/pmic@62/regulators/exten
In of_get_regulator(), the node is returned from of_parse_phandle()
with refcount incremented, after using it, of_node_put() need be called.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perce
Wiz
CVE-2025-68287 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68287 CVE-2025-68287 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68287 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: dwc3: Fix race condition between concurrent dwc3_remove_requests() call paths
dwc3_remove_requests()
dwc3_remove_requests()
dwc3_gadget_reset_interrupt()
dwc3_ep0_reset_state()
dwc3_ep0_stall_and_restart()
dwc3_ep0_out_start()
dwc3_remove_requests()
dwc3_gadget_del_and_unmap_request()
dwc3_gadget_reset_interrupt()
dwc3_stop_active_transfers()
dwc3_stop_active_transfers()
dwc3_remove_requests()
dwc3_gadget_del_and_unmap_request()
adb root
gserial_disconnect()
usb_ep_disable()
dwc3_gadget_ep_disable()
dwc3_remove_requests()
-ESHUTDOWN
Path 3 operates asynchronously and lacks synchronization with Paths
1 and 2. When Path 3 compl
Wiz
CVE-2025-68235 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68235 CVE-2025-68235 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68235 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nouveau/firmware: Add missing kfree() of nvkm_falcon_fw::boot
nvkm_falcon_fw::boot is allocated, but no one frees it. This causes a
kmemleak warning.
Make sure this data is deallocated.
Source : NVD
## 7.1
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek
kernel-uek64k-modules
Sources
NVD
CBL-Mariner 3.0 Severity HIGH Has Fix Added at: Jan 13, 2026
De
Wiz
CVE-2025-40349 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40349 CVE-2025-40349 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40349 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfs: validate record offset in hfsplus_bmap_alloc
hfsplus_bmap_alloc can trigger a crash if a
record offset or length is larger than node_size
[ 15.264282] BUG: KASAN: slab-out-of-bounds in hfsplus_bmap_alloc+0x887/0x8b0
[ 15.265192] Read of size 8 at addr ffff8881085ca188 by task test/183
[ 15.265949]
[ 15.266163] CPU: 0 UID: 0 PID: 183 Comm: test Not tainted 6.17.0-rc2-gc17b750b3ad9 #14 PREEMPT(voluntary)
[ 15.266165] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[ 15.266167] Call Trace:
[ 15.266168] [ 15.266169] dump_stack_lvl+0x53/0x70
[ 15.266173] print_report+0xd0/0x660
[ 15.266181] kasan_re
Wiz
CVE-2025-71267 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71267 CVE-2025-71267 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71267 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: ntfs3: fix infinite loop triggered by zero-sized ATTR_LIST
We found an infinite loop bug in the ntfs3 file system that can lead to a
Denial-of-Service (DoS) condition.
A malformed NTFS image can cause an infinite loop when an ATTR_LIST attribute
indicates a zero data size while the driver allocates memory for it.
When ntfs_load_attr_list() processes a resident ATTR_LIST with data_size set
to zero, it still allocates memory because of al_aligned(0). This creates an
inconsistent state where ni->attr_list.size is zero, but ni->attr_list.le is
non-null. This causes ni_enum_attr_ex to incorrectly assume that no attribute
list exists and enumerates
Wiz
CVE-2025-68376 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68376 CVE-2025-68376 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68376 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
coresight: ETR: Fix ETR buffer use-after-free issue
When ETR is enabled as CS_MODE_SYSFS, if the buffer size is changed
and enabled again, currently sysfs_buf will point to the newly
allocated memory(buf_new) and free the old memory(buf_old). But the
etr_buf that is being used by the ETR remains pointed to buf_old, not
updated to buf_new. In this case, it will result in a memory
use-after-free issue.
Fix this by checking ETR's mode before updating and releasing buf_old,
if the mode is CS_MODE_SYSFS, then skip updating and releasing it.
Source : NVD
## 6.4
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Wiz
CVE-2022-50876 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50876 CVE-2022-50876 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50876 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: musb: Fix musb_gadget.c rxstate overflow bug
The usb function device call musb_gadget_queue() adds the passed
request to musb_ep::req_list,If the (request->length > musb_ep->packet_sz)
and (is_buffer_mapped(req) return false),the rxstate() will copy all data
in fifo to request->buf which may cause request->buf out of bounds.
Fix it by add the length check :
fifocnt = min_t(unsigned, request->length - request->actual, fifocnt);
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2023-54289 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54289 CVE-2023-54289 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54289 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: qedf: Fix NULL dereference in error handling
Smatch reported:
drivers/scsi/qedf/qedf_main.c:3056 qedf_alloc_global_queues()
warn: missing unwind goto?
At this point in the function, nothing has been allocated so we can return
directly. In particular the "qedf->global_queues" have not been allocated
so calling qedf_free_global_queues() will lead to a NULL dereference when
we check if (!gl[i]) and "gl" is NULL.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Alma Linux
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Perce
Wiz
CVE-2025-68792 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68792 CVE-2025-68792 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68792 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tpm2-sessions: Fix out of range indexing in name_size
'name_size' does not have any range checks, and it just directly indexes
with TPM_ALG_ID, which could lead into memory corruption at worst.
Address the issue by only processing known values and returning -EINVAL for
unrecognized values.
Make also 'tpm_buf_append_name' and 'tpm_buf_fill_hmac_session' fallible so
that errors are detected before causing any spurious TPM traffic.
End also the authorization session on failure in both of the functions, as
the session state would be then by definition corrupted.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Ke
Wiz
CVE-2026-23290 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23290 CVE-2026-23290 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23290 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: pegasus: validate USB endpoints
The pegasus driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it. If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 9.1
Exploitation Probability (EPSS) N/A
Affected pack
Wiz
CVE-2026-23434 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23434 CVE-2026-23434 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23434 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mtd: rawnand: serialize lock/unlock against other NAND operations
nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area
without holding the NAND device lock. On controllers that implement
SET_FEATURES via multiple low-level PIO commands, these can race with
concurrent UBI/UBIFS background erase/write operations that hold the
device lock, resulting in cmd_pending conflicts on the NAND controller.
Add nand_get_device()/nand_release_device() around the lock/unlock
operations to serialize them against all other NAND controller access.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Deb
Wiz
CVE-2022-50849 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50849 CVE-2022-50849 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50849 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pstore: Avoid kcore oops by vmap()ing with VM_IOREMAP
An oops can be induced by running 'cat /proc/kcore > /dev/null' on
devices using pstore with the ram backend because kmap_atomic() assumes
lowmem pages are accessible with __va().
Unable to handle kernel paging request at virtual address ffffff807ff2b000
Mem abort info:
ESR = 0x96000006
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x06: level 2 translation fault
Data abort info:
ISV = 0, ISS = 0x00000006
CM = 0, WnR = 0
swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000081d87000
[ffffff807ff2b000] pgd=180000017fe18003, p4d=180000017fe18003, pud=180000017fe
Wiz
CVE-2025-40363 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40363 CVE-2025-40363 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40363 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: ipv6: fix field-spanning memcpy warning in AH output
Fix field-spanning memcpy warnings in ah6_output() and
ah6_output_done() where extension headers are copied to/from IPv6
address fields, triggering fortify-string warnings about writes beyond
the 16-byte address fields.
memcpy: detected field-spanning write (size 40) of single field "&top_iph->saddr" at net/ipv6/ah6.c:439 (size 16)
WARNING: CPU: 0 PID: 8838 at net/ipv6/ah6.c:439 ah6_output+0xe7e/0x14e0 net/ipv6/ah6.c:439
The warnings are false positives as the extension headers are
intentionally placed after the IPv6 header in memory. Fix by properly
copying addresses and extension headers
Wiz
CVE-2022-50699 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50699 CVE-2022-50699 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50699 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
selinux: enable use of both GFP_KERNEL and GFP_ATOMIC in convert_context()
The following warning was triggered on a hardware environment:
SELinux: Converting 162 SID table entries...
BUG: sleeping function called from invalid context at
__might_sleep+0x60/0x74 0x0
in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 5943, name: tar
CPU: 7 PID: 5943 Comm: tar Tainted: P O 5.10.0 #1
Call trace:
dump_backtrace+0x0/0x1c8
show_stack+0x18/0x28
dump_stack+0xe8/0x15c
___might_sleep+0x168/0x17c
__might_sleep+0x60/0x74
__kmalloc_track_caller+0xa0/0x7dc
kstrdup+0x54/0xac
convert_context+0x48/0x2e4
sidtab_context_to_sid+0x1c4/0x36c
security_context_to_sid_
Wiz
CVE-2023-54238 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54238 CVE-2023-54238 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54238 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mlx5: fix skb leak while fifo resync and push
During ptp resync operation SKBs were poped from the fifo but were never
freed neither by napi_consume nor by dev_kfree_skb_any. Add call to
napi_consume_skb to properly free SKBs.
Another leak was happening because mlx5e_skb_fifo_has_room() had an error
in the check. Comparing free running counters works well unless C promotes
the types to something wider than the counter. In this case counters are
u16 but the result of the substraction is promouted to int and it causes
wrong result (negative value) of the check when producer have already
overlapped but consumer haven't yet. Explicit cast to u16 fixes
Wiz
CVE-2026-23447 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23447 CVE-2026-23447 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23447 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check
The same bounds-check bug fixed for NDP16 in the previous patch also
exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated
against the total skb length without accounting for ndpoffset, allowing
out-of-bounds reads when the NDP32 is placed near the end of the NTB.
Add ndpoffset to the nframes bounds check and use struct_size_t() to
express the NDP-plus-DPE-array size more clearly.
Compile-tested only.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release D
Wiz
CVE-2026-23448 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23448 CVE-2026-23448 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23448 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check
cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE
entries fit within the skb. The first check correctly accounts for
ndpoffset:
if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len)
but the second check omits it:
if ((sizeof(struct usb_cdc_ncm_ndp16) +
ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len)
This validates the DPE array size against the total skb length as if
the NDP were at offset 0, rather than at ndpoffset. When the NDP is
placed near the end of the NTB (large wNdpIndex), the DPE entries can
extend past the skb data buffer even though
Wiz
CVE-2022-50730 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50730 CVE-2022-50730 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50730 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: silence the warning when evicting inode with dioread_nolock
When evicting an inode with default dioread_nolock, it could be raced by
the unwritten extents converting kworker after writeback some new
allocated dirty blocks. It convert unwritten extents to written, the
extents could be merged to upper level and free extent blocks, so it
could mark the inode dirty again even this inode has been marked
I_FREEING. But the inode->i_io_list check and warning in
ext4_evict_inode() missing this corner case. Fortunately,
ext4_evict_inode() will wait all extents converting finished before this
check, so it will not lead to inode use-after-free problem, e
Wiz
CVE-2026-23053 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23053 CVE-2026-23053 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23053 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
NFS: Fix a deadlock involving nfs_release_folio()
Wang Zhaolong reports a deadlock involving NFSv4.1 state recovery
waiting on kthreadd, which is attempting to reclaim memory by calling
nfs_release_folio(). The latter cannot make progress due to state
recovery being needed.
It seems that the only safe thing to do here is to kick off a writeback
of the folio, without waiting for completion, or else kicking off an
asynchronous commit.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2023-54157 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54157 CVE-2023-54157 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54157 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
binder: fix UAF of alloc->vma in race with munmap()
[ cmllamas: clean forward port from commit 015ac18be7de ("binder: fix
UAF of alloc->vma in race with munmap()") in 5.10 stable. It is needed
in mainline after the revert of commit a43cfc87caaf ("android: binder:
stop saving a pointer to the VMA") as pointed out by Liam. The commit
log and tags have been tweaked to reflect this. ]
In commit 720c24192404 ("ANDROID: binder: change down_write to
down_read") binder assumed the mmap read lock is sufficient to protect
alloc->vma inside binder_update_page_range(). This used to be accurate
until commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem
Wiz
CVE-2025-68296 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68296 CVE-2025-68296 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68296 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm, fbcon, vga_switcheroo: Avoid race condition in fbcon setup
Protect vga_switcheroo_client_fb_set() with console lock. Avoids OOB
access in fbcon_remap_all(). Without holding the console lock the call
races with switching outputs.
VGA switcheroo calls fbcon_remap_all() when switching clients. The fbcon
function uses struct fb_info.node, which is set by register_framebuffer().
As the fb-helper code currently sets up VGA switcheroo before registering
the framebuffer, the value of node is -1 and therefore not a legal value.
For example, fbcon uses the value within set_con2fb_map() [1] as an index
into an array.
Moving vga_switcheroo_client_fb_set(
Wiz
CVE-2023-53992 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53992 CVE-2023-53992 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53992 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: cfg80211: ocb: don't leave if not joined
If there's no OCB state, don't ask the driver/mac80211 to
leave, since that's just confusing. Since set/clear the
chandef state, that's a simple check.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-modules-internal
kernel-rt-debug-modules-extra
Sources
NVD
Debian 11 No Fix Added at: Dec 26, 2025
Debian 12, 13, 14
Wiz
CVE-2026-23143 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23143 [MEDIUM] CVE-2026-23143 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23143 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
virtio_net: Fix misalignment bug in struct virtnet_info
Use the new TRAILING_OVERLAP() helper to fix a misalignment bug
along with the following warning:
drivers/net/virtio_net.c:429:46: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE];
struct virtio_net_rss_config_trailer
rss_trailer.hash_key_data
rss_hash_key_data
struct virtio_net_rss_config_trailer {
__le16 max_tx_vq; /* 0 2 /
__u8 hash_key_length; / 2 1 /
__u8 hash_key_data[]; / 3 0 */
/* size: 4, cachelines: 1, members: 3 */
/* padding: 1 */
/* last cacheline: 4
Wiz
CVE-2026-22978 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 3.3
CVE-2026-22978 [LOW] CVE-2026-22978 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22978 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: avoid kernel-infoleak from struct iw_point
struct iw_point has a 32bit hole on 64bit arches.
struct iw_point {
void __user pointer; / Pointer to the data (in user space) /
__u16 length; / number of fields or size in bytes /
__u16 flags; / Optional params */
};
Make sure to zero the structure to avoid disclosing 32bits of kernel data
to user space.
Source : NVD
## 3.3
Score
Published January 23, 2026
Severity LOW
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.6
Exploitation P
Wiz
CVE-2026-23355 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23355 CVE-2026-23355 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23355 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ata: libata: cancel pending work after clearing deferred_qc
Syzbot reported a WARN_ON() in ata_scsi_deferred_qc_work(), caused by
ap->ops->qc_defer() returning non-zero before issuing the deferred qc.
ata_scsi_schedule_deferred_qc() is called during each command completion.
This function will check if there is a deferred QC, and if
ap->ops->qc_defer() returns zero, meaning that it is possible to queue the
deferred qc at this time (without being deferred), then it will queue the
work which will issue the deferred qc.
Once the work get to run, which can potentially be a very long time after
the work was scheduled, there is a WARN_ON() if ap->ops->qc
Wiz
CVE-2026-23451 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23451 CVE-2026-23451 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23451 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bonding: prevent potential infinite loop in bond_header_parse()
bond_header_parse() can loop if a stack of two bonding devices is setup,
because skb->dev always points to the hierarchy top.
Add new "const struct net_device *dev" parameter to
(struct header_ops)->parse() method to make sure the recursion
is bounded, and that the final leaf parse method is called.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Af
Wiz
CVE-2025-68304 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68304 CVE-2025-68304 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68304 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_core: lookup hci_conn on RX path on protocol side
The hdev lock/lookup/unlock/use pattern in the packet RX path doesn't
ensure hci_conn* is not concurrently modified/deleted. This locking
appears to be leftover from before conn_hash started using RCU
commit bf4c63252490b ("Bluetooth: convert conn hash to RCU")
and not clear if it had purpose since then.
Currently, there are code paths that delete hci_conn* from elsewhere
than the ordered hdev->workqueue where the RX work runs in. E.g.
commit 5af1f84ed13a ("Bluetooth: hci_sync: Fix UAF on hci_abort_conn_sync")
introduced some of these, and there probably were a few others before
it. I
Wiz
CVE-2026-23436 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23436 CVE-2026-23436 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23436 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: shaper: protect from late creation of hierarchy
We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.
The netdev may get unregistered in between the time we take
the ref and the time we lock it. We may allocate the hierarchy
after flush has already run, which would lead to a leak.
Take the instance lock in pre- already, this saves us from the race
and removes the need for dedicated lock/unlock callbacks completely.
After all, if there's any chance of write happening concurrently
with the flush - we're back to leakin
Wiz
CVE-2026-22983 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22983 [MEDIUM] CVE-2026-22983 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22983 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: do not write to msg_get_inq in callee
NULL pointer dereference fix.
msg_get_inq is an input field from caller to callee. Don't set it in
the callee, as the caller may not clear it on struct reuse.
This is a kernel-internal variant of msghdr only, and the only user
does reinitialize the field. So this is not critical for that reason.
But it is more robust to avoid the write, and slightly simpler code.
And it fixes a bug, see below.
Callers set msg_get_inq to request the input queue length to be
returned in msg_inq. This is equivalent to but independent from the
SO_INQ request to return that same info as a cmsg (tp->recvmsg_inq).
To reduce bra
Wiz
CVE-2026-1788 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 6.6
CVE-2026-1788 [MEDIUM] CVE-2026-1788 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-1788 :
Linux Ubuntu vulnerability analysis and mitigation
: Out-of-bounds Write vulnerability in Xquic Project Xquic Server xquic on Linux (QUIC protocol implementation, packet processing module modules) allows : Buffer Manipulation.This issue affects Xquic Server: through 1.8.3.
Source : NVD
## 6.6
Score
Published February 3, 2026
Severity MEDIUM
CNA Score 6.6
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Feb 04, 2026
## Get a CVE risk assessment
Get a
Wiz
CVE-2025-68170 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68170 CVE-2025-68170 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68170 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/radeon: Do not kfree() devres managed rdev
Since the allocation of the drivers main structure was changed to
devm_drm_dev_alloc() rdev is managed by devres and we shouldn't be calling
kfree() on it.
This fixes things exploding if the driver probe fails and devres cleans up
the rdev after we already free'd it.
(cherry picked from commit 16c0681617b8a045773d4d87b6140002fa75b03b)
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Pr
Wiz
CVE-2025-68814 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68814 CVE-2025-68814 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68814 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring: fix filename leak in __io_openat_prep()
__io_openat_prep() allocates a struct filename using getname(). However,
for the condition of the file being installed in the fixed file table as
well as having O_CLOEXEC flag set, the function returns early. At that
point, the request doesn't have REQ_F_NEED_CLEANUP flag set. Due to this,
the memory for the newly allocated struct filename is not cleaned up,
causing a memory leak.
Fix this by setting the REQ_F_NEED_CLEANUP for the request just after the
successful getname() call, so that when the request is torn down, the
filename will be cleaned up, along with other resources needing cleanup.
Sour
Wiz
CVE-2025-68351 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-68351 [MEDIUM] CVE-2025-68351 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68351 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
exfat: fix refcount leak in exfat_find
exfat_find
exfat_get_dentry_set
exfat_get_dentry_set
es->bh
exfat_put_dentry_set
exfat_get_dentry_set
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-socionext
python3-perf6.12
Sources
NVD
Debian 13, 14 Severity MEDIUM Has Fix Added at: Dec 26, 2025
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM
Wiz
CVE-2025-68368 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68368 CVE-2025-68368 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68368 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
md: init bioset in mddev_init
IO operations may be needed before md_run(), such as updating metadata
after writing sysfs. Without bioset, this triggers a NULL pointer
dereference as below:
BUG: kernel NULL pointer dereference, address: 0000000000000020
Call Trace:
md_update_sb+0x658/0xe00
new_level_store+0xc5/0x120
md_attr_store+0xc9/0x1e0
sysfs_kf_write+0x6f/0xa0
kernfs_fop_write_iter+0x141/0x2a0
vfs_write+0x1fc/0x5a0
ksys_write+0x79/0x180
__x64_sys_write+0x1d/0x30
x64_sys_call+0x2818/0x2880
do_syscall_64+0xa9/0x580
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Reproducer
mdadm -CR /dev/md0 -l1 -n2 /dev/sd[cd]
echo inactive > /sys/block/md0/md/array_
Wiz
CVE-2022-50776 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50776 CVE-2022-50776 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50776 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
clk: st: Fix memory leak in st_of_quadfs_setup()
If st_clk_register_quadfs_pll() fails, @lock should be freed before goto
@err_exit, otherwise will cause meory leak issue, fix it.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 15.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-livepatch-5_14_21-150500_55_133-default
linux-gcp-fips
Sources
NVD
Debian 11, 12, 13, 14 Has Fix Added at: Dec 26, 2025
Echo Has Fix Added
Wiz
CVE-2023-54231 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54231 CVE-2023-54231 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54231 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: libwx: fix memory leak in wx_setup_rx_resources
When wx_alloc_page_pool() failed in wx_setup_rx_resources(), it doesn't
release DMA buffer. Add dma_free_coherent() in the error path to release
the DMA buffer.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-aws-fips
linux-azure-fips
Sources
NVD
Ubuntu 16.04, 18.04, 20.04 Severity MEDIUM No Fix Added at: Jan 02, 2026
## Get a
Wiz
CVE-2022-50864 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50864 CVE-2022-50864 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50864 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nilfs2: fix shift-out-of-bounds due to too large exponent of block size
If field s_log_block_size of superblock data is corrupted and too large,
init_nilfs() and load_nilfs() still can trigger a shift-out-of-bounds
warning followed by a kernel panic (if panic_on_warn is set):
shift exponent 38973 is too large for 32-bit type 'int'
Call Trace: dump_stack_lvl+0xcd/0x134
ubsan_epilogue+0xb/0x50
__ubsan_handle_shift_out_of_bounds.cold.12+0x17b/0x1f5
init_nilfs.cold.11+0x18/0x1d [nilfs2]
nilfs_mount+0x9b5/0x12b0 [nilfs2]
...
This fixes the issue by adding and using a new helper function for getting
block size with sanity check.
Source : NVD
Published
Wiz
CVE-2025-71191 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71191 [MEDIUM] CVE-2025-71191 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71191 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: at_hdmac: fix device leak on of_dma_xlate()
Make sure to drop the reference taken when looking up the DMA platform
device during of_dma_xlate() when releasing channel resources.
Note that commit 3832b78b3ec2 ("dmaengine: at_hdmac: add missing
put_device() call in at_dma_xlate()") fixed the leak in a couple of
error paths but the reference is still leaking on successful allocation.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabi
Wiz
CVE-2025-68332 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68332 CVE-2025-68332 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68332 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
comedi: c6xdigio: Fix invalid PNP driver unregistration
c6xdigio_attach()
pnp_register_driver()
struct pnp_driver
name
id_table
c6xdigio_detach()
pnp_unregister_driver()
c6xdigio_attach()
pnp_register_driver()
pnp_register_driver()
pnp_unregister_driver()
c6xdigio_detach()
c6xdigio_detach()
c6xdigio_attach()
pnp_unregister_driver()
pnp_register_driver()
driver_unregister()
Also, the PNP driver registration and unregistration should be done at
module init and exit time, respectively, not when attaching or detaching
Comedi devices to the driver. (There might be more than one Comedi
device being attached to the driver, although that is
Wiz
CVE-2026-22999 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-22999 [MEDIUM] CVE-2026-22999 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-22999 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net/sched: sch_qfq: do not free existing class in qfq_change_class()
Fixes qfq_change_class() error case.
cl->qdisc and cl should only be freed if a new class and qdisc
were allocated, or we risk various UAF.
Source : NVD
## 5.5
Score
Published January 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 1.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-devel
linux-azure-6.17
Sources
NVD
CBL-Mariner 2.0 Severity MEDIUM Has Fix Add
Wiz
CVE-2026-23043 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23043 CVE-2026-23043 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23043 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix NULL pointer dereference in do_abort_log_replay()
Coverity reported a NULL pointer dereference issue (CID 1666756) in
do_abort_log_replay(). When btrfs_alloc_path() fails in
replay_one_buffer(), wc->subvol_path is NULL, but btrfs_abort_log_replay()
calls do_abort_log_replay() which unconditionally dereferences
wc->subvol_path when attempting to print debug information. Fix this by
adding a NULL check before dereferencing wc->subvol_path in
do_abort_log_replay().
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date
Wiz
CVE-2025-68326 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68326 CVE-2025-68326 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68326 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/xe/guc: Fix stack_depot usage
Add missing stack_depot_init() call when CONFIG_DRM_XE_DEBUG_GUC is
enabled to fix the following call stack:
[] BUG: kernel NULL pointer dereference, address: 0000000000000000
[] Workqueue: drm_sched_run_job_work [gpu_sched]
[] RIP: 0010:stack_depot_save_flags+0x172/0x870
[] Call Trace:
[]
[] fast_req_track+0x58/0xb0 [xe]
(cherry picked from commit 64fdf496a6929a0a194387d2bb5efaf5da2b542f)
Source : NVD
Published December 22, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probabi
Wiz
CVE-2023-54060 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54060 CVE-2023-54060 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54060 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommufd: Set end correctly when doing batch carry
Even though the test suite covers this it somehow became obscured that
this wasn't working.
The test iommufd_ioas.mock_domain.access_domain_destory would blow up
rarely.
end should be set to 1 because this just pushed an item, the carry, to the
pfns list.
Sometimes the test would blow up with:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] SMP
CPU: 5 PID: 584 Comm: iommufd Not tainted 6.5.0-rc1-dirty #1236
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1
Wiz
CVE-2025-68212 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68212 CVE-2025-68212 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68212 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs: Fix uninitialized 'offp' in statmount_string()
In statmount_string(), most flags assign an output offset pointer (offp)
which is later updated with the string offset. However, the
STATMOUNT_MNT_UIDMAP and STATMOUNT_MNT_GIDMAP cases directly set the
struct fields instead of using offp. This leaves offp uninitialized,
leading to a possible uninitialized dereference when *offp is updated.
Fix it by assigning offp for UIDMAP and GIDMAP as well, keeping the code
path consistent.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Releas
Wiz
CVE-2025-68286 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68286 CVE-2025-68286 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68286 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/amd/display: Check NULL before accessing
[WHAT]
IGT kms_cursor_legacy's long-nonblocking-modeset-vs-cursor-atomic
fails with NULL pointer dereference. This can be reproduced with
both an eDP panel and a DP monitors connected.
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 13 UID: 0 PID: 2960 Comm: kms_cursor_lega Not tainted
6.16.0-99-custom #8 PREEMPT(voluntary)
Hardware name: AMD ........
RIP: 0010:dc_stream_get_scanoutpos+0x34/0x130 [amdgpu]
Code: 57 4d 89 c7 41 56 49 89 ce 41 55 49 89 d5 41
Wiz
CVE-2023-53843 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53843 CVE-2023-53843 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53843 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: openvswitch: reject negative ifindex
Recent changes in net-next (commit 759ab1edb56c ("net: store netdevs
in an xarray")) refactored the handling of pre-assigned ifindexes
and let syzbot surface a latent problem in ovs. ovs does not validate
ifindex, making it possible to create netdev ports with negative
ifindex values. It's easy to repro with YNL:
$ ./cli.py --spec netlink/specs/ovs_datapath.yaml
--do new
--json '{"upcall-pid": 1, "name":"my-dp"}'
$ ./cli.py --spec netlink/specs/ovs_vport.yaml
--do new
--json '{"upcall-pid": "00000001", "name": "some-port0", "dp-ifindex":3,"ifindex":4294901760,"type":2}'
$ ip link show
-65536: some-port0: m
Wiz
CVE-2025-40351 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40351 CVE-2025-40351 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40351 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
hfsplus: fix KMSAN uninit-value issue in hfsplus_delete_cat()
The syzbot reported issue in hfsplus_delete_cat():
[ 70.682285][ T9333] =====================================================
[ 70.682943][ T9333] BUG: KMSAN: uninit-value in hfsplus_subfolders_dec+0x1d7/0x220
[ 70.683640][ T9333] hfsplus_subfolders_dec+0x1d7/0x220
[ 70.684141][ T9333] hfsplus_delete_cat+0x105d/0x12b0
[ 70.684621][ T9333] hfsplus_rmdir+0x13d/0x310
[ 70.685048][ T9333] vfs_rmdir+0x5ba/0x810
[ 70.685447][ T9333] do_rmdir+0x964/0xea0
[ 70.685833][ T9333] __x64_sys_rmdir+0x71/0xb0
[ 70.686260][ T9333] x64_sys_call+0xcd8/0x3cf0
[ 70.686695][ T9333] do_syscall_64+0xd9/0x1d0
[
Wiz
CVE-2025-68317 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68317 CVE-2025-68317 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68317 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/zctx: check chained notif contexts
Send zc only links ubuf_info for requests coming from the same context.
There are some ambiguous syz reports, so let's check the assumption on
notification completion.
Source : NVD
## 5.5
Score
Published December 16, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg-5.15
kernel
Sources
NVD
Container-Optimized OS Has Fix Added at:
Wiz
CVE-2026-23385 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23385 CVE-2026-23385 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23385 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: clone set on flush only
Syzbot with fault injection triggered a failing memory allocation with
GFP_KERNEL which results in a WARN splat:
iter.err
WARNING: net/netfilter/nf_tables_api.c:845 at nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845, CPU#0: syz.0.17/5992
Modules linked in:
CPU: 0 UID: 0 PID: 5992 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
RIP: 0010:nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845
Code: 8b 05 86 5a 4e 09 48 3b 84 24 a0 00 00 00 75 62 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f
Wiz
CVE-2026-23101 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 4.7
CVE-2026-23101 [MEDIUM] CVE-2026-23101 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23101 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
leds: led-class: Only Add LED to leds_list when it is fully ready
Before this change the LED was added to leds_list before led_init_core()
gets called adding it the list before led_classdev.set_brightness_work gets
initialized.
This leaves a window where led_trigger_register() of a LED's default
trigger will call led_trigger_set() which calls led_set_brightness()
which in turn will end up queueing the uninitialized led_classdev.set_brightness_work.
This race gets hit by the lenovo-thinkpad-t14s EC driver which registers
2 LEDs with a default trigger provided by snd_ctl_led.ko in quick
succession. The first led_classdev_register() causes an async m
Wiz
CVE-2026-23205 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23205 [MEDIUM] CVE-2026-23205 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23205 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb/client: fix memory leak in smb2_open_file()
Reproducer:
server: directories are exported read-only
client: mount -t cifs //${server_ip}/export /mnt
client: dd if=/dev/zero of=/mnt/file bs=512 count=1000 oflag=direct
client: umount /mnt
client: sleep 1
client: modprobe -r cifs
The error message is as follows:
## =============================================================================
BUG cifs_small_rq (Not tainted): Objects remaining on __kmem_cache_shutdown()
Object 0x00000000d47521be @offset=14336
...
WARNING: mm/slub.c:1251 at __kmem_cache_shutdown+0x34e/0x440, CPU#0: modprobe/1577
...
Call Trace: kmem_cache_destroy+0x94/0x190
c
Wiz
CVE-2022-50704 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50704 CVE-2022-50704 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50704 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
USB: gadget: Fix use-after-free during usb config switch
In the process of switching USB config from rndis to other config,
if the hardware does not support the ->pullup callback, or the
hardware encounters a low probability fault, both of them may cause
the ->pullup callback to fail, which will then cause a system panic
(use after free).
The gadget drivers sometimes need to be unloaded regardless of the
hardware's behavior.
## Analysis as follows:
(1) write /config/usb_gadget/g1/UDC "none"
gether_disconnect+0x2c/0x1f8
rndis_disable+0x4c/0x74
composite_disconnect+0x74/0xb0
configfs_composite_disconnect+0x60/0x7c
usb_gadget_disconnect+0x70/0x12
Wiz
CVE-2025-71237 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71237 [MEDIUM] CVE-2025-71237 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71237 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nilfs2: Fix potential block overflow that cause system hang
When a user executes the FITRIM command, an underflow can occur when
calculating nblocks if end_block is too small. Since nblocks is of
type sector_t, which is u64, a negative nblocks value will become a
very large positive integer. This ultimately leads to the block layer
function __blkdev_issue_discard() taking an excessively long time to
process the bio chain, and the ns_segctor_sem lock remains held for a
long period. This prevents other tasks from acquiring the ns_segctor_sem
lock, resulting in the hang reported by syzbot in [1].
If the ending block is too small, typically if it is sm
Wiz
CVE-2022-50766 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50766 CVE-2022-50766 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50766 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: set generation before calling btrfs_clean_tree_block in btrfs_init_new_buffer
syzbot is reporting uninit-value in btrfs_clean_tree_block() [1], for
commit bc877d285ca3dba2 ("btrfs: Deduplicate extent_buffer init code")
missed that btrfs_set_header_generation() in btrfs_init_new_buffer() must
not be moved to after clean_tree_block() because clean_tree_block() is
calling btrfs_header_generation() since commit 55c69072d6bd5be1 ("Btrfs:
Fix extent_buffer usage when nodesize != leafsize").
Since memzero_extent_buffer() will reset "struct btrfs_header" part, we
can't move btrfs_set_header_generation() to before memzero_extent_buffer().
Just re-add
Wiz
CVE-2026-23282 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23282 CVE-2026-23282 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23282 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix oops due to uninitialised var in smb2_unlink()
If SMB2_open_init() or SMB2_close_init() fails (e.g. reconnect), the
iovs set @rqst will be left uninitialised, hence calling
SMB2_open_free(), SMB2_close_free() or smb2_set_related() on them will
oops.
Fix this by initialising @close_iov and @open_iov before setting them
in @rqst.
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 5.9
Exploitation Probability (EPSS) N/A
Affected packages a
Wiz
CVE-2025-68169 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68169 CVE-2025-68169 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68169 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netpoll: Fix deadlock in memory allocation under spinlock
Fix a AA deadlock in refill_skbs() where memory allocation while holding
skb_pool->lock can trigger a recursive lock acquisition attempt.
The deadlock scenario occurs when the system is under severe memory
pressure:
refill_skbs() acquires skb_pool->lock (spinlock)
alloc_skb() is called while holding the lock
Memory allocator fails and calls slab_out_of_memory()
This triggers printk() for the OOM warning
The console output path calls netpoll_send_udp()
netpoll_send_udp() attempts to acquire the same skb_pool->lock
Deadlock: the lock is already held by the same CPU
Call stack:
refill_s
Wiz
CVE-2025-68222 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68222 CVE-2025-68222 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68222 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
pinctrl: s32cc: fix uninitialized memory in s32_pinctrl_desc
s32_pinctrl_desc is allocated with devm_kmalloc(), but not all of its
fields are initialized. Notably, num_custom_params is used in
pinconf_generic_parse_dt_config(), resulting in intermittent allocation
errors, such as the following splat when probing i2c-imx:
WARNING: CPU: 0 PID: 176 at mm/page_alloc.c:4795 __alloc_pages_noprof+0x290/0x300
[...]
Hardware name: NXP S32G3 Reference Design Board 3 (S32G-VNP-RDB3) (DT)
[...]
Call trace:
__alloc_pages_noprof+0x290/0x300 (P)
___kmalloc_large_node+0x84/0x168
__kmalloc_large_node_noprof+0x34/0x120
__kmalloc_noprof+0x2ac/0x378
pinconf_generic_pa
Wiz
CVE-2023-53853 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53853 CVE-2023-53853 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53853 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netlink: annotate accesses to nlk->cb_running
Both netlink_recvmsg() and netlink_native_seq_show() read
nlk->cb_running locklessly. Use READ_ONCE() there.
Add corresponding WRITE_ONCE() to netlink_dump() and
__netlink_dump_start()
syzbot reported:
BUG: KCSAN: data-race in __netlink_dump_start / netlink_recvmsg
write to 0xffff88813ea4db59 of 1 bytes by task 28219 on cpu 0:
__netlink_dump_start+0x3af/0x4d0 net/netlink/af_netlink.c:2399
netlink_dump_start include/linux/netlink.h:308 [inline]
rtnetlink_rcv_msg+0x70f/0x8c0 net/core/rtnetlink.c:6130
netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2577
rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6
Wiz
CVE-2023-54229 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54229 CVE-2023-54229 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54229 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: fix registration of 6Ghz-only phy without the full channel range
Because of what seems to be a typo, a 6Ghz-only phy for which the BDF
does not allow the 7115Mhz channel will fail to register:
WARNING: CPU: 2 PID: 106 at net/wireless/core.c:907 wiphy_register+0x914/0x954
Modules linked in: ath11k_pci sbsa_gwdt
CPU: 2 PID: 106 Comm: kworker/u8:5 Not tainted 6.3.0-rc7-next-20230418-00549-g1e096a17625a-dirty #9
Hardware name: Freebox V7R Board (DT)
Workqueue: ath11k_qmi_driver_event ath11k_qmi_driver_event_work
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : wiphy_register+0x914/0x954
lr : ieee80211_register_hw+0x67c
Wiz
CVE-2026-23240 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 9.8
CVE-2026-23240 [CRITICAL] CVE-2026-23240 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23240 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tls: Fix race condition in tls_sw_cancel_work_tx()
This issue was discovered during a code audit.
After cancel_delayed_work_sync() is called from tls_sk_proto_close(),
tx_work_handler() can still be scheduled from paths such as the
Delayed ACK handler or ksoftirqd.
As a result, the tx_work_handler() worker may dereference a freed
TLS object.
The following is a simple race scenario:
cpu0 cpu1
tls_sk_proto_close()
tls_sw_cancel_work_tx()
tls_write_space()
tls_sw_write_space()
if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
cancel_delayed_work_sync(&ctx->tx_work.work);
schedule_delayed_work
Wiz
CVE-2025-68724 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68724 CVE-2025-68724 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68724 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: asymmetric_keys - prevent overflow in asymmetric_key_generate_id
Use check_add_overflow() to guard against potential integer overflows
when adding the binary blob lengths and the size of an asymmetric_key_id
structure and return ERR_PTR(-EOVERFLOW) accordingly. This prevents a
possible buffer overflow when copying data from potentially malicious
X.509 certificate fields that can be arbitrarily large, such as ASN.1
INTEGER serial numbers, issuer names, etc.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit N
Wiz
CVE-2025-68291 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68291 CVE-2025-68291 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68291 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
mptcp: Initialise rcv_mss before calling tcp_send_active_reset() in mptcp_do_fastclose().
syzbot reported divide-by-zero in __tcp_select_window() by
MPTCP socket. [0]
We had a similar issue for the bare TCP and fixed in commit
499350a5a6e7 ("tcp: initialize rcv_mss to TCP_MIN_MSS instead
of 0").
Let's apply the same fix to mptcp_do_fastclose().
[0]:
Oops: divide error: 0000 [#1] SMP KASAN PTI
CPU: 0 UID: 0 PID: 6068 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
RIP: 0010:__tcp_select_window+0x824/0x1320 net/ipv4/tcp_output.c:3336
Code: ff ff ff 44 89
Wiz
CVE-2026-23352 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23352 CVE-2026-23352 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23352 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/efi: defer freeing of boot services memory
efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE
and EFI_BOOT_SERVICES_DATA using memblock_free_late().
There are two issue with that: memblock_free_late() should be used for
memory allocated with memblock_alloc() while the memory reserved with
memblock_reserve() should be freed with free_reserved_area().
More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
efi_free_boot_services() is called before deferred initialization of the
memory map is complete.
Benjamin Herrenschmidt reports that this causes a leak of ~140MB of
RAM on EC2 t3a.nano instances which only have 512MB or RA
Wiz
CVE-2025-68171 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68171 CVE-2025-68171 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68171 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/fpu: Ensure XFD state on signal delivery
Sean reported [1] the following splat when running KVM tests:
WARNING: CPU: 232 PID: 15391 at xfd_validate_state+0x65/0x70
Call Trace: fpu__clear_user_states+0x9c/0x100
arch_do_signal_or_restart+0x142/0x210
exit_to_user_mode_loop+0x55/0x100
do_syscall_64+0x205/0x2c0
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Chao further identified [2] a reproducible scenario involving signal
delivery: a non-AMX task is preempted by an AMX-enabled task which
modifies the XFD MSR.
When the non-AMX task resumes and reloads XSTATE with init values,
a warning is triggered due to a mismatch between fpstate::xfd and the
CPU's
Wiz
CVE-2022-50819 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50819 CVE-2022-50819 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50819 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
udmabuf: Set ubuf->sg = NULL if the creation of sg table fails
When userspace tries to map the dmabuf and if for some reason
(e.g. OOM) the creation of the sg table fails, ubuf->sg needs to be
set to NULL. Otherwise, when the userspace subsequently closes the
dmabuf fd, we'd try to erroneously free the invalid sg table from
release_udmabuf resulting in the following crash reported by syzbot:
general protection fault, probably for non-canonical address
0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 0 PID: 3609 Comm: syz-executor487 Not tainted
5.19.0-syzkaller-13930-g7ebfc8
Wiz
CVE-2025-68777 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68777 CVE-2025-68777 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68777 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Input: ti_am335x_tsc - fix off-by-one error in wire_order validation
The current validation 'wire_order[i] > ARRAY_SIZE(config_pins)' allows
wire_order[i] to equal ARRAY_SIZE(config_pins), which causes out-of-bounds
access when used as index in 'config_pins[wire_order[i]]'.
Since config_pins has 4 elements (indices 0-3), the valid range for
wire_order should be 0-3. Fix the off-by-one error by using >= instead
of > in the validation check.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploi
Wiz
CVE-2026-23016 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23016 [MEDIUM] CVE-2026-23016 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23016 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
inet: frags: drop fraglist conntrack references
Jakub added a warning in nf_conntrack_cleanup_net_list() to make debugging
leaked skbs/conntrack references more obvious.
syzbot reports this as triggering, and I can also reproduce this via
ip_defrag.sh selftest:
conntrack cleanup blocked for 60s
WARNING: net/netfilter/nf_conntrack_core.c:2512
[..]
conntrack clenups gets stuck because there are skbs with still hold nf_conn
references via their frag_list.
net.core.skb_defer_max=0 makes the hang disappear.
Eric Dumazet points out that skb_release_head_state() doesn't follow the
fraglist.
ip_defrag.sh can only reproduce this problem since
commit 64
Wiz
CVE-2026-23007 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23007 [MEDIUM] CVE-2026-23007 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23007 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: zero non-PI portion of auto integrity buffer
The auto-generated integrity buffer for writes needs to be fully
initialized before being passed to the underlying block device,
otherwise the uninitialized memory can be read back by userspace or
anyone with physical access to the storage device. If protection
information is generated, that portion of the integrity buffer is
already initialized. The integrity data is also zeroed if PI generation
is disabled via sysfs or the PI tuple size is 0. However, this misses
the case where PI is generated and the PI tuple size is nonzero, but the
metadata size is larger than the PI tuple. In this case, the r
Wiz
CVE-2023-54309 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54309 CVE-2023-54309 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54309 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
tpm: tpm_vtpm_proxy: fix a race condition in /dev/vtpmx creation
/dev/vtpmx is made visible before 'workqueue' is initialized, which can
lead to a memory corruption in the worst case scenario.
Address this by initializing 'workqueue' as the very first step of the
driver initialization.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-lowlatency
kernel-zfcpdump-modules-
Wiz
CVE-2025-68195 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68195 CVE-2025-68195 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68195 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/CPU/AMD: Add missing terminator for zen5_rdseed_microcode
Running x86_match_min_microcode_rev() on a Zen5 CPU trips up KASAN for an out
of bounds access.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux openSUSE
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-mediatek
kernel-default-vdso
Sources
NVD
## Get a CVE risk assessment
Get a prioritized view of CVEs in your cloud—so you can focus on what's exploitable, not j
Wiz
CVE-2022-50827 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50827 CVE-2022-50827 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50827 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: lpfc: Fix memory leak in lpfc_create_port()
Commit 5e633302ace1 ("scsi: lpfc: vmid: Add support for VMID in mailbox
command") introduced allocations for the VMID resources in
lpfc_create_port() after the call to scsi_host_alloc(). Upon failure on the
VMID allocations, the new code would branch to the 'out' label, which
returns NULL without unwinding anything, thus skipping the call to
scsi_host_put().
Fix the problem by creating a separate label 'out_free_vmid' to unwind the
VMID resources and make the 'out_put_shost' label call only
scsi_host_put(), as was done before the introduction of allocations for
VMID.
Source : NVD
Published Decembe
Wiz
CVE-2025-71082 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71082 [HIGH] CVE-2025-71082 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71082 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: btusb: revert use of devm_kzalloc in btusb
This reverts commit 98921dbd00c4e ("Bluetooth: Use devm_kzalloc in
btusb.c file").
In btusb_probe(), we use devm_kzalloc() to allocate the btusb data. This
ties the lifetime of all the btusb data to the binding of a driver to
one interface, INTF. In a driver that binds to other interfaces, ISOC
and DIAG, this is an accident waiting to happen.
The issue is revealed in btusb_disconnect(), where calling
usb_driver_release_interface(&btusb_driver, data->intf) will have devm
free the data that is also being used by the other interfaces of the
driver that may not be released yet.
To fix this, revert
Wiz
CVE-2026-23103 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2026-23103 [HIGH] CVE-2026-23103 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23103 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ipvlan: Make the addrs_lock be per port
Make the addrs_lock be per port, not per ipvlan dev.
Initial code seems to be written in the assumption,
that any address change must occur under RTNL.
But it is not so for the case of IPv6. So
Introduce per-port addrs_lock.
It was needed to fix places where it was forgotten
to take lock (ipvlan_open/ipvlan_close)
This appears to be a very minor problem though.
Since it's highly unlikely that ipvlan_add_addr() will
be called on 2 CPU simultaneously. But nevertheless,
this could cause:
False-negative of ipvlan_addr_busy(): one interfaceiterated through all port->ipvlans + ipvlan->addrsunder some ipvlan sp
Wiz
CVE-2023-54000 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54000 CVE-2023-54000 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54000 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: hns3: fix deadlock issue when externel_lb and reset are executed together
When externel_lb and reset are executed together, a deadlock may
occur:
[ 3147.217009] INFO: task kworker/u321:0:7 blocked for more than 120 seconds.
[ 3147.230483] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 3147.238999] task:kworker/u321:0 state:D stack: 0 pid: 7 ppid: 2 flags:0x00000008
[ 3147.248045] Workqueue: hclge hclge_service_task [hclge]
[ 3147.253957] Call trace:
[ 3147.257093] __switch_to+0x7c/0xbc
[ 3147.261183] __schedule+0x338/0x6f0
[ 3147.265357] schedule+0x50/0xe0
[ 3147.269185] schedule_preempt_disabled+0x18/0x24
[ 3147.27
Wiz
CVE-2025-68257 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68257 CVE-2025-68257 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68257 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
comedi: check device's attached status in compat ioctls
Syzbot identified an issue [1] that crashes kernel, seemingly due to
unexistent callback dev->get_valid_routes(). By all means, this should
not occur as said callback must always be set to
get_zero_valid_routes() in __comedi_device_postconfig().
As the crash seems to appear exclusively in i386 kernels, at least,
judging from [1] reports, the blame lies with compat versions
of standard IOCTL handlers. Several of them are modified and
do not use comedi_unlocked_ioctl(). While functionality of these
ioctls essentially copy their original versions, they do not
have required sanity check for device
Wiz
CVE-2025-68343 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68343 CVE-2025-68343 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68343 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing header
The driver expects to receive a struct gs_host_frame in
gs_usb_receive_bulk_callback().
Use struct_group to describe the header of the struct gs_host_frame and
check that we have at least received the header before accessing any
members of it.
To resubmit the URB, do not dereference the pointer chain
"dev->parent->hf_size_rx" but use "parent->hf_size_rx" instead. Since
"urb->context" contains "parent", it is always defined, while "dev" is not
defined if the URB it too short.
Source : NVD
## 5.1
Score
Published December 23, 2025
Severity MEDIUM
CNA Scor
Wiz
CVE-2025-71071 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71071 [HIGH] CVE-2025-71071 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71071 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommu/mediatek: fix use-after-free on probe deferral
The driver is dropping the references taken to the larb devices during
probe after successful lookup as well as on errors. This can
potentially lead to a use-after-free in case a larb device has not yet
been bound to its driver so that the iommu driver probe defers.
Fix this by keeping the references as expected while the iommu driver is
bound.
Source : NVD
## 7.8
Score
Published January 13, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Prob
Wiz
CVE-2022-50754 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50754 CVE-2022-50754 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50754 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
apparmor: fix a memleak in multi_transaction_new()
In multi_transaction_new(), the variable t is not freed or passed out
on the failure of copy_from_user(t->data, buf, size), which could lead
to a memleak.
Fix this bug by adding a put_multi_transaction(t) in the error path.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dlm-kmp-default
kernel-syms
Sources
NVD
Debian 11,
Wiz
CVE-2026-23021 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23021 [MEDIUM] CVE-2026-23021 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23021 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: usb: pegasus: fix memory leak in update_eth_regs_async()
When asynchronously writing to the device registers and if usb_submit_urb()
fail, the code fail to release allocated to this point resources.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 3.2
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-obs-build
kernel-source
Sources
NVD
CBL-Mariner 3.0 Severity MEDIUM Has Fix Added at
Wiz
CVE-2023-53847 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-53847 CVE-2023-53847 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-53847 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb-storage: alauda: Fix uninit-value in alauda_check_media()
Syzbot got KMSAN to complain about access to an uninitialized value in
the alauda subdriver of usb-storage:
BUG: KMSAN: uninit-value in alauda_transport+0x462/0x57f0
drivers/usb/storage/alauda.c:1137
CPU: 0 PID: 12279 Comm: usb-storage Not tainted 5.3.0-rc7+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x191/0x1f0 lib/dump_stack.c:113
kmsan_report+0x13a/0x2b0 mm/kmsan/kmsan_report.c:108
__msan_warning+0x73/0xe0 mm/kmsan/kmsan_instr.c:250
alauda_check_media+0x344/0x3310 drivers
Wiz
CVE-2025-71220 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71220 [HIGH] CVE-2025-71220 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71220 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smb/server: call ksmbd_session_rpc_close() on error path in create_smb2_pipe()
When ksmbd_iov_pin_rsp() fails, we should call ksmbd_session_rpc_close().
Source : NVD
## 7.8
Score
Published February 14, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 2.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump
kernel-uek64k-modules-core
Sources
NVD
Debian 11, 12, 13, 14 Severity HIGH Has Fix Added at: Feb 15, 2026
Echo Severity HIGH
Wiz
CVE-2022-50841 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50841 CVE-2022-50841 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50841 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Add overflow check for attribute size
The offset addition could overflow and pass the used size check given an
attribute with very large size (e.g., 0xffffff7f) while parsing MFT
attributes. This could lead to out-of-bound memory R/W if we try to
access the next attribute derived by Add2Ptr(attr, asize)
[ 32.963847] BUG: unable to handle page fault for address: ffff956a83c76067
[ 32.964301] #PF: supervisor read access in kernel mode
[ 32.964526] #PF: error_code(0x0000) - not-present page
[ 32.964893] PGD 4dc01067 P4D 4dc01067 PUD 0
[ 32.965316] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 32.965727] CPU: 0 PID: 243 Comm: mount Not tainted 5.19.0+
Wiz
CVE-2026-23457 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23457 CVE-2026-23457 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23457 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp()
sip_help_tcp() parses the SIP Content-Length header with
simple_strtoul(), which returns unsigned long, but stores the result in
unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are
silently truncated before computing the SIP message boundary.
For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32,
causing the parser to miscalculate where the current message ends. The
loop then treats trailing data in the TCP segment as a second SIP
message and processes it through the SDP parser.
Fix this by changing clen to unsigned long to match the re
Wiz
CVE-2026-23039 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23039 CVE-2026-23039 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23039 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/gud: fix NULL fb and crtc dereferences on USB disconnect
On disconnect drm_atomic_helper_disable_all() is called which
sets both the fb and crtc for a plane to NULL before invoking a commit.
This causes a kernel oops on every display disconnect.
Add guards for those dereferences.
Source : NVD
Published January 31, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 1.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-64k-debug-modules-partner
kernel-debu
Wiz
CVE-2022-50727 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50727 CVE-2022-50727 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50727 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
scsi: efct: Fix possible memleak in efct_device_init()
In efct_device_init(), when efct_scsi_reg_fc_transport() fails,
efct_scsi_tgt_driver_exit() is not called to release memory for
efct_scsi_tgt_driver_init() and causes memleak:
unreferenced object 0xffff8881020ce000 (size 2048):
comm "modprobe", pid 465, jiffies 4294928222 (age 55.872s)
backtrace:
[] kmalloc_trace+0x27/0x110
[] target_register_template+0x4fd/0x7b0 [target_core_mod]
[] efct_scsi_tgt_driver_init+0x18/0x50 [efct]
[] 0xffffffffc0d90011
[] do_one_initcall+0xd0/0x4e0
[] do_init_module+0x1cc/0x6a0
...
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Lin
Wiz
CVE-2023-54303 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54303 CVE-2023-54303 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54303 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Disable preemption in bpf_perf_event_output
The nesting protection in bpf_perf_event_output relies on disabled
preemption, which is guaranteed for kprobes and tracepoints.
However bpf_perf_event_output can be also called from uprobes context
through bpf_prog_run_array_sleepable function which disables migration,
but keeps preemption enabled.
This can cause task to be preempted by another one inside the nesting
protection and lead eventually to two tasks using same perf_sample_data
buffer and cause crashes like:
kernel tried to execute NX-protected page - exploit attempt? (uid: 0)
BUG: unable to handle page fault for address: ffffffff82be3eea
Wiz
CVE-2025-68341 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68341 CVE-2025-68341 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68341 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
veth: reduce XDP no_direct return section to fix race
As explain in commit fa349e396e48 ("veth: Fix race with AF_XDP exposing
old or uninitialized descriptors") for veth there is a chance after
napi_complete_done() that another CPU can manage start another NAPI
instance running veth_pool(). For NAPI this is correctly handled as the
napi_schedule_prep() check will prevent multiple instances from getting
scheduled, but for the remaining code in veth_pool() this can run
concurrent with the newly started NAPI instance.
The problem/race is that xdp_clear_return_frame_no_direct() isn't
designed to be nested.
Prior to commit 401cb7dae813 ("net: Reference
Wiz
CVE-2022-50728 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50728 CVE-2022-50728 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50728 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
s390/lcs: Fix return type of lcs_start_xmit()
With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
proposed warning in clang aims to catch these at compile time, which
reveals:
drivers/s390/net/lcs.c:2090:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device )' (aka 'enum netdev_tx ( )(struct sk_buff
Wiz
CVE-2023-54113 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54113 CVE-2023-54113 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54113 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
rcu: dump vmalloc memory info safely
Currently, for double invoke call_rcu(), will dump rcu_head objects memory
info, if the objects is not allocated from the slab allocator, the
vmalloc_dump_obj() will be invoke and the vmap_area_lock spinlock need to
be held, since the call_rcu() can be invoked in interrupt context,
therefore, there is a possibility of spinlock deadlock scenarios.
And in Preempt-RT kernel, the rcutorture test also trigger the following
lockdep warning:
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0
preempt_count: 1, e
Wiz
CVE-2026-23094 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23094 [MEDIUM] CVE-2026-23094 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23094 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
uacce: fix isolate sysfs check condition
uacce supports the device isolation feature. If the driver
implements the isolate_err_threshold_read and
isolate_err_threshold_write callback functions, uacce will create
sysfs files now. Users can read and configure the isolation policy
through sysfs. Currently, sysfs files are created as long as either
isolate_err_threshold_read or isolate_err_threshold_write callback
functions are present.
However, accessing a non-existent callback function may cause the
system to crash. Therefore, intercept the creation of sysfs if
neither read nor write exists; create sysfs if either is supported,
but intercept unsuppor
Wiz
CVE-2026-23360 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23360 CVE-2026-23360 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23360 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme: fix admin queue leak on controller reset
When nvme_alloc_admin_tag_set() is called during a controller reset,
a previous admin queue may still exist. Release it properly before
allocating a new one to avoid orphaning the old queue.
This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix
admin request_queue lifetime").
Source : NVD
Published March 25, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.3
Exploitation Probability (EPSS) N/A
Affected packages and libr
Wiz
CVE-2023-54005 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54005 CVE-2023-54005 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54005 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
binder: fix memory leak in binder_init()
In binder_init(), the destruction of binder_alloc_shrinker_init() is not
performed in the wrong path, which will cause memory leaks. So this commit
introduces binder_alloc_shrinker_exit() and calls it in the wrong path to
fix that.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
gfs2-kmp-default
kernel-default-livepatch-devel
Sources
Wiz
CVE-2023-54138 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54138 CVE-2023-54138 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54138 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
drm/msm: fix NULL-deref on irq uninstall
In case of early initialisation errors and on platforms that do not use
the DPU controller, the deinitilisation code can be called with the kms
pointer set to NULL.
Patchwork: https://patchwork.freedesktop.org/patch/525104/
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-intel-iotg
kernel-devel-rt
Sources
NVD
Debian 12, 13, 1
Wiz
CVE-2026-23423 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23423 CVE-2026-23423 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23423 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: free pages on error in btrfs_uring_read_extent()
In this function the 'pages' object is never freed in the hopes that it is
picked up by btrfs_uring_read_finished() whenever that executes in the
future. But that's just the happy path. Along the way previous
allocations might have gone wrong, or we might not get -EIOCBQUEUED from
btrfs_encoded_read_regular_fill_pages(). In all these cases, we go to a
cleanup section that frees all memory allocated by this function without
assuming any deferred execution, and this also needs to happen for the
'pages' allocation.
Source : NVD
Published April 3, 2026
CNA Score N/A
Affected Technologies
Linux
Wiz
CVE-2022-50740 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50740 CVE-2022-50740 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50740 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath9k: hif_usb: fix memory leak of urbs in ath9k_hif_usb_dealloc_tx_urbs()
Syzkaller reports a long-known leak of urbs in
ath9k_hif_usb_dealloc_tx_urbs().
The cause of the leak is that usb_get_urb() is called but usb_free_urb()
(or usb_put_urb()) is not called inside usb_kill_urb() as urb->dev or
urb->ep fields have not been initialized and usb_kill_urb() returns
immediately.
The patch removes trying to kill urbs located in hif_dev->tx.tx_buf
because hif_dev->tx.tx_buf is not supposed to contain urbs which are in
pending state (the pending urbs are stored in hif_dev->tx.tx_pending).
The tx.tx_lock is acquired so there should not be any chang
Wiz
CVE-2026-23259 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23259 CVE-2026-23259 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23259 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/rw: free potentially allocated iovec on cache put failure
If a read/write request goes through io_req_rw_cleanup() and has an
allocated iovec attached and fails to put to the rw_cache, then it may
end up with an unaccounted iovec pointer. Have io_rw_recycle() return
whether it recycled the request or not, and use that to gauge whether to
free a potential iovec or not.
Source : NVD
## 5.5
Score
Published March 18, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (E
Wiz
CVE-2023-54313 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54313 CVE-2023-54313 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54313 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ovl: fix null pointer dereference in ovl_get_acl_rcu()
Following process:
P1 P2
path_openat
link_path_walk
may_lookup
inode_permission(rcu)
ovl_permission
acl_permission_check
check_acl
get_cached_acl_rcu
ovl_get_inode_acl
realinode = ovl_inode_real(ovl_inode)
drop_cache
__dentry_kill(ovl_dentry)
iput(ovl_inode)
ovl_destroy_inode(ovl_inode)
dput(oi->__upperdentry)
dentry_kill(upperdentry)
dentry_unlink_inode
upperdentry->d_inode = NULL
ovl_inode_upper
upperdentry = ovl_i_dentry_upper(ovl_inode)
d_inode(upperdentry) // returns NULL
IS_POSIXACL(realinode) // NULL pointer dereference
, will trigger an null pointer dereference at realinode:
[ 205.472797
Wiz
CVE-2023-54081 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54081 CVE-2023-54081 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54081 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
xen: speed up grant-table reclaim
When a grant entry is still in use by the remote domain, Linux must put
it on a deferred list. Normally, this list is very short, because
the PV network and block protocols expect the backend to unmap the grant
first. However, Qubes OS's GUI protocol is subject to the constraints
of the X Window System, and as such winds up with the frontend unmapping
the window first. As a result, the list can grow very large, resulting
in a massive memory leak and eventual VM freeze.
To partially solve this problem, make the number of entries that the VM
will attempt to free at each iteration tunable. The default is still
10, but
Wiz
CVE-2022-50745 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50745 CVE-2022-50745 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50745 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
staging: media: tegra-video: fix device_node use after free
At probe time this code path is followed:
saves into chan->of_node a pointer to the channel OF node
automatically gets and puts 'channel'
now the node saved in chan->of_node has refcount 0, can disappear
tegra_csi_channel_init -- uses chan->of_node
After that, chan->of_node keeps storing the node until the device is
removed.
of_node_get() the node and of_node_put() it during teardown to avoid any
risk.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CI
Wiz
CVE-2025-68294 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68294 CVE-2025-68294 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68294 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
io_uring/net: ensure vectored buffer node import is tied to notification
When support for vectored registered buffers was added, the import
itself is using 'req' rather than the notification io_kiocb, sr->notif.
For non-vectored imports, sr->notif is correctly used. This is important
as the lifetime of the two may be different. Use the correct io_kiocb
for the vectored buffer import.
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation P
Wiz
CVE-2023-54023 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54023 CVE-2023-54023 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54023 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix race between balance and cancel/pause
Syzbot reported a panic that looks like this:
assertion failed: fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED, in fs/btrfs/ioctl.c:465
------------[ cut here ]------------
kernel BUG at fs/btrfs/messages.c:259!
RIP: 0010:btrfs_assertfail+0x2c/0x30 fs/btrfs/messages.c:259
Call Trace: btrfs_exclop_balance fs/btrfs/ioctl.c:465 [inline]
btrfs_ioctl_balance fs/btrfs/ioctl.c:3564 [inline]
btrfs_ioctl+0x531e/0x5b30 fs/btrfs/ioctl.c:4632
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:870 [inline]
__se_sys_ioctl fs/ioctl.c:856 [inline]
__x64_sys_ioctl+0x197/0x210 fs/ioctl.c:856
do_sy
Wiz
CVE-2026-23141 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23141 [MEDIUM] CVE-2026-23141 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23141 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: send: check for inline extents in range_is_hole_in_parent()
Before accessing the disk_bytenr field of a file extent item we need
to check if we are dealing with an inline extent.
This is because for inline extents their data starts at the offset of
the disk_bytenr field. So accessing the disk_bytenr
means we are accessing inline data or in case the inline data is less
than 8 bytes we can actually cause an invalid
memory access if this inline extent item is the first item in the leaf
or access metadata from other items.
Source : NVD
## 5.5
Score
Published February 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Ker
Wiz
CVE-2022-50811 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50811 CVE-2022-50811 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50811 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
erofs: fix missing unmap if z_erofs_get_extent_compressedlen() fails
Otherwise, meta buffers could be leaked.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
bpftool
kernel-64k-debug-modules-partner
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 9 Severity LOW Has Fix Added at: Dec 31, 2025
Ubuntu 16.04, 18.04, 2
Wiz
CVE-2023-54009 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54009 CVE-2023-54009 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54009 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
i2c: cadence: cdns_i2c_master_xfer(): Fix runtime PM leak on error path
The cdns_i2c_master_xfer() function gets a runtime PM reference when the
function is entered. This reference is released when the function is
exited. There is currently one error path where the function exits
directly, which leads to a leak of the runtime PM reference.
Make sure that this error path also releases the runtime PM reference.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile
Wiz
CVE-2025-68359 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68359 CVE-2025-68359 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68359 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix double free of qgroup record after failure to add delayed ref head
In the previous code it was possible to incur into a double kfree()
scenario when calling add_delayed_ref_head(). This could happen if the
record was reported to already exist in the
btrfs_qgroup_trace_extent_nolock() call, but then there was an error
later on add_delayed_ref_head(). In this case, since
add_delayed_ref_head() returned an error, the caller went to free the
record. Since add_delayed_ref_head() couldn't set this kfree'd pointer
to NULL, then kfree() would have acted on a non-NULL 'record' object
which was pointing to memory already freed by the callee.
The p
Wiz
CVE-2026-23040 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23040 CVE-2026-23040 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23040 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211_hwsim: fix typo in frequency notification
The NAN notification is for 5745 MHz which corresponds to channel 149
and not 5475 which is not actually a valid channel. This could result in
a NULL pointer dereference in cfg80211_next_nan_dw_notif.
Source : NVD
Published February 4, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-debug-modules-partner
kernel-rt-modules-partner
Sources
NVD
Deb
Wiz
CVE-2022-50763 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50763 CVE-2022-50763 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50763 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: marvell/octeontx - prevent integer overflows
The "code_length" value comes from the firmware file. If your firmware
is untrusted realistically there is probably very little you can do to
protect yourself. Still we try to limit the damage as much as possible.
Also Smatch marks any data read from the filesystem as untrusted and
prints warnings if it not capped correctly.
The "code_length * 2" can overflow. The round_up(ucode_size, 16) +
sizeof() expression can overflow too. Prevent these overflows.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV
Wiz
CVE-2022-50815 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50815 CVE-2022-50815 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50815 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext2: Add sanity checks for group and filesystem size
Add sanity check that filesystem size does not exceed the underlying
device size and that group size is big enough so that metadata can fit
into it. This avoid trying to mount some crafted filesystems with
extremely large group counts.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-5.4
linux-ibm-5.4
Sources
Wiz
CVE-2025-71095 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71095 [MEDIUM] CVE-2025-71095 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71095 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: stmmac: fix the crash issue for zero copy XDP_TX action
There is a crash issue when running zero copy XDP_TX action, the crash
log is shown below.
[ 216.122464] Unable to handle kernel paging request at virtual address fffeffff80000000
[ 216.187524] Internal error: Oops: 0000000096000144 [#1] SMP
[ 216.301694] Call trace:
[ 216.304130] dcache_clean_poc+0x20/0x38 (P)
[ 216.308308] __dma_sync_single_for_device+0x1bc/0x1e0
[ 216.313351] stmmac_xdp_xmit_xdpf+0x354/0x400
[ 216.317701] __stmmac_xdp_run_prog+0x164/0x368
[ 216.322139] stmmac_napi_poll_rxtx+0xba8/0xf00
[ 216.326576] __napi_poll+0x40/0x218
[ 216.408054] Kernel panic - not syncing: Oops:
Wiz
CVE-2026-23242 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.5
CVE-2026-23242 [HIGH] CVE-2026-23242 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23242 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
RDMA/siw: Fix potential NULL pointer dereference in header processing
If siw_get_hdr() returns -EINVAL before set_rx_fpdu_context(),
qp->rx_fpdu can be NULL. The error path in siw_tcp_rx_data()
dereferences qp->rx_fpdu->more_ddp_segs without checking, which
may lead to a NULL pointer deref. Only check more_ddp_segs when
rx_fpdu is present.
KASAN splat:
[ 101.384271] KASAN: null-ptr-deref in range [0x00000000000000c0-0x00000000000000c7]
[ 101.385869] RIP: 0010:siw_tcp_rx_data+0x13ad/0x1e50
Source : NVD
## 7.5
Score
Published March 18, 2026
Severity HIGH
CNA Score 7.5
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
H
Wiz
CVE-2025-68730 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68730 CVE-2025-68730 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68730 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
accel/ivpu: Fix page fault in ivpu_bo_unbind_all_bos_from_context()
Don't add BO to the vdev->bo_list in ivpu_gem_create_object().
When failure happens inside drm_gem_shmem_create(), the BO is not
fully created and ivpu_gem_bo_free() callback will not be called
causing a deleted BO to be left on the list.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.8
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-nvidia-lowlatency
Wiz
CVE-2023-54043 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54043 CVE-2023-54043 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54043 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommufd: Do not add the same hwpt to the ioas->hwpt_list twice
The hwpt is added to the hwpt_list only during its creation, it is never
added again. This hunk is some missed leftover from rework. Adding it
twice will corrupt the linked list in some cases.
It effects HWPT specific attachment, which is something the test suite
cannot cover until we can create a legitimate struct device with a
non-system iommu "driver" (ie we need the bus removed from the iommu code)
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CI
Wiz
CVE-2025-71190 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71190 [MEDIUM] CVE-2025-71190 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71190 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
dmaengine: bcm-sba-raid: fix device leak on probe
Make sure to drop the reference taken when looking up the mailbox device
during probe on probe failures and on driver unbind.
Source : NVD
## 5.5
Score
Published January 31, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.5
Exploitation Probability (EPSS) N/A
Affected packages and libraries
linux-azure-6.8
kernel-64kb-optional
Sources
NVD
CBL-Mariner 3.0 Severity MEDIUM Has Fix Added at: Mar 13, 2026
Debian
Wiz
CVE-2023-54071 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54071 CVE-2023-54071 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54071 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtw88: use work to update rate to avoid RCU warning
The ieee80211_ops::sta_rc_update must be atomic, because
ieee80211_chan_bw_change() holds rcu_read lock while calling
drv_sta_rc_update(), so create a work to do original things.
Voluntary context switch within RCU read-side critical section!
WARNING: CPU: 0 PID: 4621 at kernel/rcu/tree_plugin.h:318
rcu_note_context_switch+0x571/0x5d0
CPU: 0 PID: 4621 Comm: kworker/u16:2 Tainted: G W OE
Workqueue: phy3 ieee80211_chswitch_work [mac80211]
RIP: 0010:rcu_note_context_switch+0x571/0x5d0
Call Trace: __schedule+0xb0/0x1460
? __mod_timer+0x116/0x360
schedule+0x5a/0xc0
schedule_timeout+0x87/0x150
? t
Wiz
CVE-2023-54300 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54300 CVE-2023-54300 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54300 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx
For the reasons also described in commit b383e8abed41 ("wifi: ath9k: avoid
uninit memory read in ath9k_htc_rx_msg()"), ath9k_htc_rx_msg() should
validate pkt_len before accessing the SKB.
For example, the obtained SKB may have been badly constructed with
pkt_len = 8. In this case, the SKB can only contain a valid htc_frame_hdr
but after being processed in ath9k_htc_rx_msg() and passed to
ath9k_wmi_ctrl_rx() endpoint RX handler, it is expected to have a WMI
command header which should be located inside its data payload.
Implement sanity checking inside ath9k_wmi_ctrl_rx(). Otherwise,
Wiz
CVE-2025-68734 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68734 CVE-2025-68734 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68734 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
isdn: mISDN: hfcsusb: fix memory leak in hfcsusb_probe()
In hfcsusb_probe(), the memory allocated for ctrl_urb gets leaked when
setup_instance() fails with an error code. Fix that by freeing the urb
before freeing the hw structure. Also change the error paths to use the
goto ladder style.
Compile tested only. Issue found using a prototype static analysis tool.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Wiz
CVE-2025-68172 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68172 CVE-2025-68172 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68172 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: aspeed - fix double free caused by devm
The clock obtained via devm_clk_get_enabled() is automatically managed
by devres and will be disabled and freed on driver detach. Manually
calling clk_disable_unprepare() in error path and remove function
causes double free.
Remove the manual clock cleanup in both aspeed_acry_probe()'s error
path and aspeed_acry_remove().
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.4
Exploitation Probability (EP
Wiz
CVE-2026-23397 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23397 CVE-2026-23397 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23397 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nfnetlink_osf: validate individual option lengths in fingerprints
nfnl_osf_add_callback() validates opt_num bounds and string
NUL-termination but does not check individual option length fields.
A zero-length option causes nf_osf_match_one() to enter the option
matching loop even when foptsize sums to zero, which matches packets
with no TCP options where ctx->optp is NULL:
Oops: general protection fault
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98)
Call Trace:
nf_osf_match (net/netfilter/nfnetlink_osf.c:227)
xt_osf_match_packet (net/netfilter/xt_osf.c:32)
ipt_do_t
Wiz
CVE-2025-68245 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68245 CVE-2025-68245 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68245 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
net: netpoll: fix incorrect refcount handling causing incorrect cleanup
commit efa95b01da18 ("netpoll: fix use after free") incorrectly
ignored the refcount and prematurely set dev->npinfo to NULL during
netpoll cleanup, leading to improper behavior and memory leaks.
Scenario causing lack of proper cleanup:
Keep in mind that npinfo is shared among all netpoll instances. In
this case, there is just one.
Now dev->npinfo->refcnt = 2;
There is just one npinfo associated to the netdev.
RCU_INIT_POINTER(np->dev->npinfo, NULL);
Set dev->npinfo = NULL, without proper cleanup
No ->ndo_netpoll_cleanup() is either called
This leaks npinfo and skbpool s
Wiz
CVE-2025-40342 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40342 CVE-2025-40342 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40342 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
nvme-fc: use lock accessing port_state and rport state
nvme_fc_unregister_remote removes the remote port on a lport object at
any point in time when there is no active association. This races with
with the reconnect logic, because nvme_fc_create_association is not
taking a lock to check the port_state and atomically increase the
active count on the rport.
Source : NVD
## 6.4
Score
Published December 9, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitati
Wiz
CVE-2025-40330 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-40330 CVE-2025-40330 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-40330 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: Shutdown FW DMA in bnxt_shutdown()
The netif_close() call in bnxt_shutdown() only stops packet DMA. There
may be FW DMA for trace logging (recently added) that will continue. If
we kexec to a new kernel, the DMA will corrupt memory in the new kernel.
Add bnxt_hwrm_func_drv_unrgtr() to unregister the driver from the FW.
This will stop the FW DMA. In case the call fails, call pcie_flr() to
reset the function and stop the DMA.
Source : NVD
Published December 9, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation
Wiz
CVE-2026-23359 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23359 CVE-2026-23359 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23359 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix stack-out-of-bounds write in devmap
get_upper_ifindexes() iterates over all upper devices and writes their
indices into an array without checking bounds.
Also the callers assume that the max number of upper devices is
MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack,
but that assumption is not correct and the number of upper devices could
be larger than MAX_NEST_DEV (e.g., many macvlans), causing a
stack-out-of-bounds write.
Add a max parameter to get_upper_ifindexes() to avoid the issue.
When there are too many upper devices, return -EOVERFLOW and abort the
redirect.
To reproduce, create more than MAX_NEST_DEV(8)
Wiz
CVE-2025-68759 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68759 CVE-2025-68759 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68759 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtl818x: Fix potential memory leaks in rtl8180_init_rx_ring()
In rtl8180_init_rx_ring(), memory is allocated for skb packets and DMA
allocations in a loop. When an allocation fails, the previously
successful allocations are not freed on exit.
Fix that by jumping to err_free_rings label on error, which calls
rtl8180_free_rx_ring() to free the allocations. Remove the free of
rx_ring in rtl8180_init_rx_ring() error path, and set the freed
priv->rx_buf entry to null, to avoid double free.
Source : NVD
Published January 5, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA
Wiz
CVE-2025-68750 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68750 CVE-2025-68750 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68750 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: potential integer overflow in usbg_make_tpg()
The variable tpgt in usbg_make_tpg() is defined as unsigned long and is
assigned to tpgt->tport_tpgt, which is defined as u16. This may cause an
integer overflow when tpgt is greater than USHRT_MAX (65535). I
haven't tried to trigger it myself, but it is possible to trigger it
by calling usbg_make_tpg() with a large value for tpgt.
I modified the type of tpgt to match tpgt->tport_tpgt and adjusted the
relevant code accordingly.
This patch is similar to commit 59c816c1f24d ("vhost/scsi: potential
memory corruption").
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Wiz
CVE-2025-68176 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68176 CVE-2025-68176 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68176 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
PCI: cadence: Check for the existence of cdns_pcie::ops before using it
cdns_pcie::ops might not be populated by all the Cadence glue drivers. This
is going to be true for the upcoming Sophgo platform which doesn't set the
ops.
Hence, add a check to prevent NULL pointer dereference.
[mani: reworded subject and description]
Source : NVD
Published December 16, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation Probability (EPSS) 0.1
Affected packages and libraries
ker
Wiz
CVE-2025-71268 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-71268 CVE-2025-71268 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71268 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix reservation leak in some error paths when inserting inline extent
If we fail to allocate a path or join a transaction, we return from
__cow_file_range_inline() without freeing the reserved qgroup data,
resulting in a leak. Fix this by ensuring we call btrfs_qgroup_free_data()
in such cases.
Source : NVD
Published March 18, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 6.3
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-rt-trace-kvm
linux-gcp-
Wiz
CVE-2026-23107 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23107 [MEDIUM] CVE-2026-23107 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23107 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
arm64/fpsimd: signal: Allocate SSVE storage when restoring ZA
The code to restore a ZA context doesn't attempt to allocate the task's
sve_state before setting TIF_SME. Consequently, restoring a ZA context
can place a task into an invalid state where TIF_SME is set but the
task's sve_state is NULL.
In legitimate but uncommon cases where the ZA signal context was NOT
created by the kernel in the context of the same task (e.g. if the task
is saved/restored with something like CRIU), we have no guarantee that
sve_state had been allocated previously. In these cases, userspace can
enter streaming mode without trapping while sve_state is NULL, causing a
l
Wiz
CVE-2023-54146 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54146 CVE-2023-54146 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54146 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
x86/kexec: Fix double-free of elf header buffer
After
b3e34a47f989 ("x86/kexec: fix memory leak of elf header buffer"),
freeing image->elf_headers in the error path of crash_load_segments()
is not needed because kimage_file_post_load_cleanup() will take
care of that later. And not clearing it could result in a double-free.
Drop the superfluous vfree() call at the error path of
crash_load_segments().
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS)
Wiz
CVE-2025-68731 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68731 CVE-2025-68731 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68731 :
Linux Ubuntu vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
accel/amdxdna: Fix an integer overflow in aie2_query_ctx_status_array()
The unpublished smatch static checker reported a warning.
drivers/accel/amdxdna/aie2_pci.c:904 aie2_query_ctx_status_array()
warn: potential user controlled sizeof overflow
'args->num_element * args->element_size' '1-u32max(user) * 1-u32max(user)'
Even this will not cause a real issue, it is better to put a reasonable
limitation for element_size and num_element. Add condition to make sure
the input element_size <= 4K and num_element <= 1K.
Source : NVD
Published December 24, 2025
CNA Score N/A
Affected Technologies
Linux Ubuntu
Has Public Exploit No
Has CISA KEV Exploit
Wiz
CVE-2026-23006 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23006 [MEDIUM] CVE-2026-23006 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23006 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ASoC: tlv320adcx140: fix null pointer
The "snd_soc_component" in "adcx140_priv" was only used once but never
set. It was only used for reaching "dev" which is already present in
"adcx140_priv".
Source : NVD
## 5.5
Score
Published January 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 0.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
dtb-exynos
kernel-livepatch-6_4_0-150700_53_31-default
Sources
NVD
Debian 11 Severity MEDIUM Has Fix
Wiz
CVE-2023-54196 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54196 CVE-2023-54196 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54196 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
fs/ntfs3: Fix NULL pointer dereference in 'ni_write_inode'
Syzbot found the following issue:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000016
Mem abort info:
ESR = 0x0000000096000006
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x06: level 2 translation fault
Data abort info:
ISV = 0, ISS = 0x00000006
CM = 0, WnR = 0
user pgtable: 4k pages, 48-bit VAs, pgdp=000000010af56000
[0000000000000016] pgd=08000001090da003, p4d=08000001090da003, pud=08000001090ce003, pmd=0000000000000000
Internal error: Oops: 0000000096000006 [#1] PREEMPT SMP
Modules linked in:
CPU: 1 PID: 3036 Comm: s
Wiz
CVE-2023-54299 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54299 CVE-2023-54299 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54299 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
usb: typec: bus: verify partner exists in typec_altmode_attention
Some usb hubs will negotiate DisplayPort Alt mode with the device
but will then negotiate a data role swap after entering the alt
mode. The data role swap causes the device to unregister all alt
modes, however the usb hub will still send Attention messages
even after failing to reregister the Alt Mode. type_altmode_attention
currently does not verify whether or not a device's altmode partner
exists, which results in a NULL pointer error when dereferencing
the typec_altmode and typec_altmode_ops belonging to the altmode
partner.
Verify the presence of a device's altmode partner before
Wiz
CVE-2025-68820 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68820 CVE-2025-68820 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68820 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
ext4: xattr: fix null pointer deref in ext4_raw_inode()
If ext4_get_inode_loc() fails (e.g. if it returns -EFSCORRUPTED),
iloc.bh will remain set to NULL. Since ext4_xattr_inode_dec_ref_all()
lacks error checking, this will lead to a null pointer dereference
in ext4_raw_inode(), called right after ext4_get_inode_loc().
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Source : NVD
Published January 13, 2026
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 16.5
Exploitation
Wiz
CVE-2025-68733 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68733 CVE-2025-68733 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68733 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
smack: fix bug: unprivileged task can create labels
If an unprivileged task is allowed to relabel itself
(/smack/relabel-self is not empty),
it can freely create new labels by writing their
names into own /proc/PID/attr/smack/current
This occurs because do_setattr() imports
the provided label in advance,
before checking "relabel-self" list.
This change ensures that the "relabel-self" list
is checked before importing the label.
Source : NVD
## 5.5
Score
Published December 24, 2025
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA K
Wiz
CVE-2025-68303 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68303 CVE-2025-68303 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68303 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
platform/x86: intel: punit_ipc: fix memory corruption
This passes the address of the pointer "&punit_ipcdev" when the intent
was to pass the pointer itself "punit_ipcdev" (without the ampersand).
This means that the:
complete(&ipcdev->cmd_complete);
in intel_punit_ioc() will write to a wrong memory address corrupting it.
Source : NVD
## 7.8
Score
Published December 16, 2025
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 10.8
Exploitation Probability (EPSS) N/A
Affecte
Wiz
CVE-2022-50852 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2022-50852 CVE-2022-50852 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2022-50852 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: mt76: mt7921: fix use after free in mt7921_acpi_read()
Don't dereference "sar_root" after it has been freed.
Source : NVD
Published December 30, 2025
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7.7
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-zfcpdump-devel-matched
kernel-zfcpdump-modules-core
Sources
NVD
Debian 12, 13, 14 Has Fix Added at: Dec 31, 2025
Echo Has Fix Added at: Dec 31, 2025
Red Hat 8, 9 Severity MEDIUM No Fix Added at: Dec 31,
Wiz
CVE-2025-71100 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 7.8
CVE-2025-71100 [HIGH] CVE-2025-71100 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71100 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
wifi: rtlwifi: 8192cu: fix tid out of range in rtl92cu_tx_fill_desc()
TID getting from ieee80211_get_tid() might be out of range of array size
of sta_entry->tids[], so check TID is less than MAX_TID_COUNT. Othwerwise,
UBSAN warn:
UBSAN: array-index-out-of-bounds in drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c:514:30
index 10 is out of range for type 'rtl_tid_data [9]'
Source : NVD
## 7.8
Score
Published January 13, 2026
Severity HIGH
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (E
Wiz
CVE-2023-54239 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2023-54239 CVE-2023-54239 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2023-54239 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
iommufd: Check for uptr overflow
syzkaller found that setting up a map with a user VA that wraps past zero
can trigger WARN_ONs, particularly from pin_user_pages weirdly returning 0
due to invalid arguments.
Prevent creating a pages with a uptr and size that would math overflow.
WARNING: CPU: 0 PID: 518 at drivers/iommu/iommufd/pages.c:793 pfn_reader_user_pin+0x2e6/0x390
Modules linked in:
CPU: 0 PID: 518 Comm: repro Not tainted 6.3.0-rc2-eeac8ede1755+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:pfn_reader_user_pin+0x2e6/0x390
Code: b1 11 e9 25 fe ff ff e8 28 e4 0
Wiz
CVE-2025-71146 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71146 [MEDIUM] CVE-2025-71146 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71146 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conncount: fix leaked ct in error paths
There are some situations where ct might be leaked as error paths are
skipping the refcounted check and return immediately. In order to solve
it make sure that the check is always called.
Source : NVD
## 5.5
Score
Published January 23, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 4.4
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-uek-debug-modules-extra-netfilter
kernel-uek-modu
Wiz
CVE-2025-68756 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2025-68756 CVE-2025-68756 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-68756 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
block: Use RCU in blk_mq_[un]quiesce_tagset() instead of set->tag_list_lock
blk_mq_{add,del}_queue_tag_set() functions add and remove queues from
tagset, the functions make sure that tagset and queues are marked as
shared when two or more queues are attached to the same tagset.
Initially a tagset starts as unshared and when the number of added
queues reaches two, blk_mq_add_queue_tag_set() marks it as shared along
with all the queues attached to it. When the number of attached queues
drops to 1 blk_mq_del_queue_tag_set() need to mark both the tagset and
the remaining queues as unshared.
Both functions need to freeze current queues in tagset before
Wiz
CVE-2026-23320 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz
CVE-2026-23320 CVE-2026-23320 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23320 :
Linux Kernel vulnerability analysis and mitigation
Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.
Source : NVD
## 5.5
Score
Published March 25, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
Linux Debian
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) N/A
Exploitation Probability (EPSS) N/A
Affected packages and libraries
kernel-core
kernel-rt-64k-debug-modules-extra
Sources
NVD
Debian 11, 12, 13 No Fix Added at: Mar 26, 2026
Debian 14 Has Fix Added at: Mar 26, 2026
Echo Has Fix Added at: Mar 26, 2026
Red Hat 10 Severity MEDIUM No Fix Added at: Mar 26, 2026
Ubuntu 16.04, 18.04, 20.04, 22
Wiz
CVE-2025-71131 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2025-71131 [MEDIUM] CVE-2025-71131 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2025-71131 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
crypto: seqiv - Do not use req->iv after crypto_aead_encrypt
As soon as crypto_aead_encrypt is called, the underlying request
may be freed by an asynchronous completion. Thus dereferencing
req->iv after it returns is invalid.
Instead of checking req->iv against info, create a new variable
unaligned_info and use it for that purpose instead.
Source : NVD
## 5.5
Score
Published January 14, 2026
Severity MEDIUM
CNA Score N/A
Affected Technologies
Linux Kernel
CBL Mariner
Has Public Exploit No
Has CISA KEV Exploit No
CISA KEV Release Date N/A
CISA KEV Due Date N/A
Exploitation Probability Percentile (EPSS) 7
Exploitation Probability (EP
Wiz
CVE-2026-23108 Impact, Exploitability, and Mitigation Steps | Wiz
blogs_wiz·CVSS 5.5
CVE-2026-23108 [MEDIUM] CVE-2026-23108 Impact, Exploitability, and Mitigation Steps | Wiz
## CVE-2026-23108 :
Linux Kernel vulnerability analysis and mitigation
In the Linux kernel, the following vulnerability has been resolved:
can: usb_8dev: usb_8dev_read_bulk_callback(): fix URB memory leak
Fix similar memory leak as in commit 7352e1d5932a ("can: gs_usb:
gs_usb_receive_bulk_callback(): fix URB memory leak").
In usb_8dev_open() -> usb_8dev_start(), the URBs for USB-in transfers are
allocated, added to the priv->rx_submitted anchor and submitted. In the
complete callback usb_8dev_read_bulk_callback(), the URBs are processed and
resubmitted. In usb_8dev_close() -> unlink_all_urbs() the URBs are freed by
calling usb_kill_anchored_urbs(&priv->rx_submitted).
However, this does not take into account that the USB framework unanchors
the URB before the complete function is call
Bugzilla
CVE-2026-31406 kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
bugzilla·2026-04-06
CVE-2026-31406 [MEDIUM] CVE-2026-31406 kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
CVE-2026-31406 kernel: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_
2026-04-06
Published