CVE-2026-41523
vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 취약점
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
- 대응 우선순위
- 점검
- CVSS
- 7.5
- EPSS
- 0.75% 백분위 51.3% · 2026.08.04 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.06.23