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.
References
Configurations
History
No history.
Information
Published : 2026-06-22 23:16
Updated : 2026-09-04 13:19
NVD link : CVE-2026-41523
Mitre link : CVE-2026-41523
CVE.ORG link : CVE-2026-41523
JSON object : View
Products Affected
vllm
- vllm
