CVE-2026-41523
HIGH severity · CVSS 7.5 · Code injection
7.5CVSS HIGH
Summary
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.
Impact & exploitability
Attack vectorNetwork
Attack complexityHigh
Privileges requiredNone
User interactionRequired
Confidentiality impactHigh
Integrity impactHigh
Availability impactHigh
Exploit probability (EPSS)1%
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products we track (1)
Recommendation
Apply the vendor fix promptly. Open any affected product above for its exact safe version.
Official patch: https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3 ↗
Additional information
- NVD record
- https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3Patch
- https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64cAdvisory
- https://access.redhat.com/errata/RHSA-2026:36005
- https://access.redhat.com/errata/RHSA-2026:36006
- https://access.redhat.com/errata/RHSA-2026:57380
- https://access.redhat.com/errata/RHSA-2026:57387
- https://access.redhat.com/errata/RHSA-2026:57389
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3rAdvisory