- CVSS
- CRITICAL · 10v3.1CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- Published
- 2025-04-30
- Weakness
- CWE-502
- Source
- nvd.nist.gov/vuln/detail/CVE-2025-32444
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.
References
- https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179
- https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2025-32444 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.