CVE-2026-41349
published 2026-04-23CVE-2026-41349: OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch…
PriorityP259high8.8CVSS 3.1
AVNACLPRLUINSUCHIHAH
EPSS
0.47%
37.4th percentile
OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent.
Affected
1 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| openclaw | openclaw | < 2026.3.28 | 2026.3.28 |
CVSS provenance
nvdv3.18.8HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
nvdv4.08.7HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
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.
VulDB
OpenClaw up to 2026.3.27 config.patch authorization (GHSA-v3qc-wrwx-j3pw / WID-SEC-2026-0948)
vuldb·2026-04-28·CVSS 8.7
CVE-2026-41349 [HIGH] OpenClaw up to 2026.3.27 config.patch authorization (GHSA-v3qc-wrwx-j3pw / WID-SEC-2026-0948)
A vulnerability identified as critical has been detected in OpenClaw up to 2026.3.27. This impacts an unknown function. The manipulation of the argument config.patch leads to missing authorization.
This vulnerability is documented as CVE-2026-41349. The attack can be initiated remotely. There is not any exploit available.
You should upgrade the affected component.
GHSA
GHSA-7f25-vhj7-mxrc: OpenClaw before 2026
ghsa_unreviewed·2026-04-24
CVE-2026-41349 [HIGH] CWE-862 GHSA-7f25-vhj7-mxrc: OpenClaw before 2026
OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent.
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2026-04-23
Published