CVE-2026-100653
vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation
- Published
- Updated
- Reserved
- Assigned by
- VulnCheck
Description
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 to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.
Public exploit
A reference of the record is tagged as an exploit or proof of concept: anyone can try it against an unpatched system. CISA's SSVC rates its exploitation: a proof of concept is public.
- GitHub Security Advisory (GHSA-hhv2-872h-628q) (opens in a new tab)vendor-advisoryexploit
Timeline
ID reserved
By VulnCheck
Published
- 5 days later
· 5 days later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| VulnCheckCNA (assigner) | 4.0 | High8.3 | 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 |
| VulnCheckCNA (assigner) | 3.1 | Medium6.5 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N |
| NVDNVD · Analyzed | 4.0 | High8.3 | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
- EPSS (exploitation in 30 days)
- 0.34% · top 72% of all CVEs (7 Nov 2026)
- CISA SSVC
- Exploitation: poc · Automatable: no · Technical impact: partial
The list uses the assigner's score when there is one, then CISA's, then NVD's: High 8.3.
Weakness
Affected products
- affected 0.22.1 – < 0.28.0
- unaffected 0.28.0
References (3)
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisories (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://trackcve.app/cve/CVE-2026-100653)Record last updated .