Advisory

PYSEC-2026-2300

Also known as: CVE-2026-41523, GHSA-q8gq-377p-jq3r

Summary

The record has no summary.

Details

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.

Severity

High Basis: CVSS v3 score 7.5, vector CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

Dates

Published
2026-06-22 23:16 UTC
Modified
2026-07-13 07:15 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0, fixed 0.22.0 (ecosystem)

Fixed versions

0.22.0

Fix

  • Fixed version 0.22.0
    pip install --upgrade vllm==0.22.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences