CVE-2026-100653: vllm · Use of Less Trusted Source
Affects vllmSource CVE Database V5
Mentioned vulnerabilities
Not known to be exploited · CVSS 8.3 High : upgrade to 0.28.0 soon.
Data as of 9 Nov 2026, 23:24 UTC
- EPSS
- 0.3% chance of exploitation in 30 days – higher than 27% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.28.0
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 26 Sep 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 10 Nov 2026.
What to do
Upgrade vllm to 0.28.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| vllm-projectvllm | Affected
| Fixed in
|
PyPIvllmpkg:pypi/vllmOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade to vLLM version 0.28.0 or later, where this issue is fixed. Until then, be aware that pinned revisions may not fully enforce artifact versioning for the affected components. No additional mitigations are indicated as this is not a remote code execution or trust bypass vulnerability.
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.