Description
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.
References
- www.cve.org/CVERecord ↗
- nvd.nist.gov/vuln/detail/CVE-2026-114053 ↗
- github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e ↗
- github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m ↗
- www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision ↗
Related CVEs
← CVE Index: search every CVE from the last 30 days
This product uses the NVD API but is not endorsed or certified by the NVD. CVSS scores do not establish exploitation.