| Component | vLLM |
| Severity | high (CVSS 8.1) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2026-10-21 |
| Affected versions | >= 0.7.3, < 0.31.0 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | 0.31.0 |
| Weakness | CWE-94 |
| CISA KEV | not listed |
NVD 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.
What to do
- Upgrade vLLM to
0.31.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-114053
- https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e
- https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m
- https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision