Advisory record · GHSA-hhv2-872h-628q

vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated ...

CVSS 8.3 HighEPSS 0.0034 · 27th percentile

Published by the GitHub Advisory Database at 26 Sept 2026, 14:16 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
vllmPyPI>=0.22.1, <0.28.00.28.0
Identifiers
GHSA-hhv2-872h-628q · CVE-2026-100653 · PYSEC-2026-4324
Weakness (CWE)
CWE-348
Published
26 Sept 2026
Updated
23 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

vLLM versions from 0.22.1 through 0.28.0 do not apply the operator's model revision pin to some Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures. Processor, tokenizer, and config files for these models can be fetched from the repository's default branch, so an upstream change can alter behavior even when a reviewed revision is pinned. The source describes this as a reproducibility and supply-chain integrity issue, not remote code execution. Upgrade vLLM to version 0.28.0 or later.

Written 1 Nov 2026.

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

ScoreRatingCVSSVectorSource
8.3 High 4.0 CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N CNA (VulnCheck)
  • CISA KEV Not listed.
  • EPSS 0.0034, the 27th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:08 UTC First seen by agentprime
  2. 31 Oct 2026, 14:08 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.