CVE-2026-47155
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.22.0 | 0.22.0 |
Affected products
3Patches
Vulnerability mechanics
References
7- github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6nvdPatchWEB
- github.com/advisories/GHSA-3ww4-5jv9-j5gmghsaADVISORY
- github.com/vllm-project/vllm/security/advisories/GHSA-3ww4-5jv9-j5gmnvdThird Party AdvisoryWEB
- huntr.com/bounties/3f1e24c0-87d2-4f6c-a705-820f380879acnvdThird Party AdvisoryWEB
- nvd.nist.gov/vuln/detail/CVE-2026-47155ghsaADVISORY
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2301.yamlghsaWEB
- github.com/vllm-project/vllm/pull/42616nvdIssue TrackingWEB
News mentions
0No linked articles in our index yet.