CVE-2025-32444 Details
Description
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.
A remote code execution vulnerability exists in vLLM versions 0.6.5 prior to 0.8.5, when integrated with Mooncake. The issue arises from using pickle-based serialization over unsecured ZeroMQ sockets, which were configured to listen on all network interfaces. This setup increased the risk of an attacker reaching the vulnerable sockets to execute an attack. Instances of vLLM that do not use the Mooncake integration are not vulnerable.
Users can upgrade to vLLM version 0.8.5 or later to address this vulnerability.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Apr 30, 2025References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-502 | Deserialization of Untrusted Data | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | >= 0.6.5, < 0.8.5 |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| May 28, 2025 | Initial Analysis | [email protected] |
| Apr 30, 2025 | New CVE Received | [email protected] |