CVE-2026-114053
highvLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients se…
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.
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H Affected products
Not reported by the source (unknown — not "none").
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
No vendor advisory or patch reference tagged by NVD. Check the references below.
References
- https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e disclosure@vulncheck.com
- https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-... disclosure@vulncheck.com