CVE-2026-114053
CVE-2026-114053 · vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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 9.2 · Critical · EPSS 0.5% · Fix available
- Published
- Updated
Affected products and versions
vllm
- Versions
- ≥ 0.7.3, < 0.31.0: Affected (semver)
- 0.31.0: Not affected (semver)
Update to 0.31.0
Original sources
- https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m
- https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e
- https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision
- https://nvd.nist.gov/vuln/detail/CVE-2026-114053