Cloudanix VulnDB

CVE-2026-41523

High · 7.5

CVSS

7.5

EPSS

0.9%

Published

Jun 22, 2026

CISA due date

—

The record

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 packages

Ecosystem Package Introduced Fixed

Related vulnerabilities