CVE-2026-41523
vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server
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.
- CVSS
- 7.5
- EPSS
- 0.75% 51.3% percentile
- CISA KEV
- Not listed
- Published
- 2026.06.23