CVE-2025-32444
Last modified
CVE-2025-32444 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. 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. EPSS estimates a 1.47% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.6.5, < 0.8.5 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5Exploit, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-32444?
How severe is CVE-2025-32444?
How do I fix CVE-2025-32444?
Are you affected by CVE-2025-32444?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST