High
8.1
vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to...
CVE-2026-114053
First seen on SecPulse
Original description The description as published by the source.
vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.
Source: NIST National Vulnerability Database NVD GitHub Advisory
References
- web github.com
- web github.com
- web vulncheck.com
- web nvd.nist.gov
- web github.com