Advisory

PYSEC-2025-42

Also known as: CVE-2025-32444, GHSA-hj4w-hm2g-p6w5

Summary

The record has no summary.

Details

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack. vLLM instances that do not make use of the mooncake integration are not vulnerable. This issue has been patched in version 0.8.5.

Severity

Critical Basis: CVSS v3 score 9.8, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Dates

Published
2025-04-30 01:15 UTC
Modified
2026-06-10 17:14 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.6.5, fixed 0.8.5 (ecosystem)

Fixed versions

0.8.5

Fix

  • Fixed version 0.8.5
    pip install --upgrade vllm==0.8.5

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