CVE-2026-41523

High

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.

SeverityHigh

CVSS7.5

Exploit probability60. percentile0.9%

ProductVllm

PublishedJun 22, 2026

First seenJun 22, 2026

Weakness typeCWE-94Code injection CWE-617CWE-617

How to fix

Update

vllm vllm0.22.0 or later
vllm0.22.0 or later

Vendor advisories

Affected products

Product	Affected versions	Fixed in
vllm vllm	v < 0.22.0	0.22.0
vllmPyPI	v < 0.22.0	0.22.0

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.