cbcvebase.
CVE-2026-41523
published 2026-06-22

CVE-2026-41523: vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading…

PriorityP352high7.5CVSS 3.1
AVNACHPRNUIRSUCHIHAH
EPSS
0.46%
36.7th percentile
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

Affected

16 ranges
VendorProductVersion rangeFixed in
rhaiivllm-cpu-rhel9
rhaiivllm-cuda-rhel9
rhaiivllm-gaudi-rhel9
rhaiivllm-rocm-rhel9
rhaiivllm-spyre-rhel9
rhelai3bootc-aws-cuda-rhel9
rhelai3bootc-azure-cuda-rhel9
rhelai3bootc-azure-rocm-rhel9
rhelai3bootc-cuda-rhel9
rhelai3bootc-gaudi-rhel9
rhelai3bootc-gcp-cuda-rhel9
rhelai3bootc-rocm-rhel9
rhoaiodh-vllm-gaudi-rhel9
vllm-projectvllm< 0.22.00.22.0
vllmvllm< 0.22.00.22.0
vllmvllm>= 0 < 0.22.00.22.0

CVSS provenance

nvdv3.17.5HIGHCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
vendor_redhat7.5HIGH
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.