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.

Classification

CVE ID: CVE-2025-32444

CVSS Base Severity: CRITICAL

CVSS Base Score: 10.0

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Affected Products

Vendor: vllm-project

Product: vllm

Exploit Prediction Scoring System (EPSS)

EPSS Score: 0.5% (probability of being exploited)

EPSS Percentile: 64.75% (scored less or equal to compared to others)

EPSS Date: 2025-05-29 (when was this score calculated)

Stakeholder-Specific Vulnerability Categorization (SSVC)

SSVC Exploitation: none

SSVC Technical Impact: total

SSVC Automatable: true

References

https://nvd.nist.gov/vuln/detail/CVE-2025-32444
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://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c
https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179

Timeline