CVE-2026-100653

CVE-2026-100653 is a medium-severity vulnerability with a CVSS 3.x base score of 6.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-348.

Key facts

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.

Frequently asked questions

What is CVE-2026-100653?
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.
How severe is CVE-2026-100653?
CVE-2026-100653 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with high attack complexity, requires no privileges and no user interaction. Impact on confidentiality is low, integrity high, and availability none.
Is CVE-2026-100653 being actively exploited?
It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (19th percentile), an estimate of the probability of exploitation in the next 30 days.
How do I fix CVE-2026-100653?
Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
When was CVE-2026-100653 published?
CVE-2026-100653 was published on 2026-09-26 and last updated on 2026-09-30.

References

Other CWE-348 vulnerabilities

Browse all CWE-348 vulnerabilities →