CVE-2026-114053
HIGH severity · CVSS 8.1 · Code injection
8.1CVSS HIGH
Summary
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.
Impact & exploitability
Attack vectorNetwork
Attack complexityHigh
Privileges requiredNone
User interactionNone
Confidentiality impactHigh
Integrity impactHigh
Availability impactHigh
Exploit probability (EPSS)0%
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products we track (1)
Recommendation
Apply the vendor fix promptly. Open any affected product above for its exact safe version.
Official patch: https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e ↗