CVE-2026-41523: Vllm

High severity, CVSS 7.5. EPSS: 0.9% chance of exploitation in the next 30 days.

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.

Affected products

• Vllm Vllm: before 0.22.0 (fixed in 0.22.0)

Published 2026-06-22. Last modified 2026-09-04.