CVE-2026-27893
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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.
- 대응 우선순위
- 점검
- CVSS
- 8.8
- EPSS
- 1.35% 백분위 68.7% · 2026.08.04 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.03.27