vllm
Affected
- introduced
0.6.5, fixed0.8.5(ecosystem)
Fixed versions
0.8.5
Fix
- Fixed version
0.8.5pip install --upgrade vllm==0.8.5
Advisory
Also known as: CVE-2025-32444, GHSA-hj4w-hm2g-p6w5
The record has no summary.
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.
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
0.6.5, fixed 0.8.5 (ecosystem)0.8.5
0.8.5pip install --upgrade vllm==0.8.5Fix 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
Source: PyPA Advisory Database · CC BY 4.0