CVSS 9.2 (critical) · published 2026-10-21
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.
Affected products (NVD): vllm vllm
Fixed in (NVD): 0.31.0
Weakness: CWE-94
Source: NVD CVE-2026-114053
Connect an AI agent to the FixLane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.