CVE-2026-22807
vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 3.3 취약점
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fix...
- 대응 우선순위
- 점검
- CVSS
- 9.8
- EPSS
- 0.73% 백분위 50.6% · 2026.08.03 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.01.22