VULNERABILITY INTELLIGENCE

CVE-2026-41523

CVSS score7.5 HIGH
EPSS probability0.91%
CISA KEVNot currently listed
Published2026-06-22
Last modified2026-10-25
CVSS vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

Description

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.

Weakness classification

  • security-advisories@github.com: CWE-94
  • 0b0ca135-0b70-47e7-9f44-1890c2a1c46c: CWE-617

Primary references