Description
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.
Affected products
vllm: vllm
References4
- github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b04… Patch
- github.com/vllm-project/vllm/pull/42616 Issue Tracking
- github.com/vllm-project/vllm/security/advisories/GHSA-3ww4-5jv9… Third Party Advisory
- huntr.com/bounties/3f1e24c0-87d2-4f6c-a705-820f380879ac Third Party Advisory
Metrics
- CVSS 3.1
-
6.5
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N - EPSS — exploit probability
- 0% percentile: 16 · as of 16 November 2026
- CWE
- CWE-345
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.