Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.22.0 do not apply revision pins consistently to all artifacts loaded for a model, so a deployment that sets a model or code revision can still load dynamic code, GGUF files, image processors, or side weights from an unpinned default revision. The source describes this as an integrity issue rather than a remote code execution flaw, and the attacker would need to change those artifacts in the upstream repository. Upgrade vLLM to 0.22.0 or later, which the source lists as the fixed version.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.5 | Medium | 3.1 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0025, the 16th percentile, on 9 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:29 UTC First seen by agentprime
- 31 Oct 2026, 14:29 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-3ww4-5jv9-j5gm
- OSV: GHSA-3ww4-5jv9-j5gm
- github.com/vllm-project/vllm/security/advisories/GHSA-3ww4-5jv9-j5gm
- nvd.nist.gov/vuln/detail/CVE-2026-47155
- github.com/vllm-project/vllm/pull/42616
- github.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2301.yaml
- github.com/vllm-project/vllm
- huntr.com/bounties/3f1e24c0-87d2-4f6c-a705-820f380879ac