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 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.
- CVSS 3.1
- 7.5
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H - EPSS
- 0.9% chance of exploitation in the next 30 days; higher than 59% of CVEs (scores of 2026-10-25)
- CWEs
- CWE-94, CWE-617
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-q8gq-377p-jq3r | PyPI | vllm | <0.22.0 | 0.22.0 |
| PYSEC-2026-2300 | PyPI | vllm | <0.22.0 | 0.22.0 |
References
- https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c
- https://access.redhat.com/errata/RHSA-2026:36005
- https://access.redhat.com/errata/RHSA-2026:36006