Vulnerability in Vllm
CVE-2026-47155
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N.
EPSS exploit prediction
EPSS 0.002, 16.4th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.22.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-3ww4-5jv9-j5gm (Third Party Advisory)
- https://github.com/vllm-project/vllm/pull/42616 (Issue Tracking)
- https://github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6 (Patch)
- https://huntr.com/bounties/3f1e24c0-87d2-4f6c-a705-820f380879ac (Third Party Advisory)