עברית

Vulnerability Intelligence

CVE-2026-41523

High 7.5

Published
Last modified
NVD status
Modified

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.

Affected products

vllm: vllm

References10

Metrics

CVSS 3.1
7.5 HIGH Score source: CNA CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS — exploit probability
1% percentile: 61 · as of 16 November 2026
CWE
CWE-94CWE-617

Could this be exploited in your environment?

A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.