Browse / AI Framework and Platform Flaws / CVE-2025-32444
vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- Class
- AI Framework and Platform Flaws (filed by a model that read the source)
- Technique
- Code and command execution
- Affected
- vllm (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
- EPSS
- 1.8% chance of exploitation in 30 days
How it works, in short
The Mooncake KV transfer integration calls recv_pyobj over a ZeroMQ socket listening on all interfaces, so attacker-sent pickle data runs code when deserialised. (Our summary, written by a model. The source text is below.)
Details
Impacted Deployments
Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.
Description
vLLM integration with mooncake is vaulnerable 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.
This is a similar to GHSA - x3m8 - f7g5 - qhm7, the problem is in
https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179
Here recv_pyobj() Contains implicit pickle.loads(), which leads to potential RCE.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
- https://nvd.nist.gov/vuln/detail/CVE-2025-32444
- https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-42.yaml
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179
Source: GitHub Advisory Database, used under CC BY 4.0.