CVE-2026-100653: vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation

Severity: medium (CVSS 6.5 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.3% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-09-26 · updated 2026-10-20
Weakness: CWE-348

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.

Affected products

vllm-project vllm: from 0.22.1 before 0.28.0 — fixed in 0.28.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.28.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-100653 or the next vulnerability affects your stack