CVE-2026-100653 vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation
vLLM fails to propagate model revision pins for specific architectures, allowing upstream changes to alter behavior in pinned deployments.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-100653?
CVE-2026-100653 is a high-severity vulnerability in Vllm Vllm, published on 26 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-348
Which versions are affected by CVE-2026-100653?
1 open source package ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.22.1 | 0.28.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-100653?
Upgrade vllm to 0.28.0 or later.
Is CVE-2026-100653 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-100653 exists.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-hhv2-872h-628q, GHSA-r3cf-2wgr-7xh9, MINI-mv84-q9fg-9xv8, MINI-rgg5-f64q-xh58, PYSEC-2026-4324.