CVE-2025-32444

moderate-risk
Published 2025-04-30

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.

Do I need to act?

~
2.5% chance of exploitation in next 30 days
EPSS score — moderate exploit probability
-
Not on CISA KEV list
No confirmed active exploitation reported to CISA
+
Fix available
Upgrade to: ba41cc90e8ef7f236347b2f1599eec2cbb9e1f0d
10
CVSS 10.0/10 Critical
NETWORK / LOW complexity

Affected Products (1)

Affected Vendors

Vllm

References (4)

Product https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43...
Patch https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab56...
Exploit https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5
Not Applicable https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
44
/ 100
moderate-risk
Severity 33/34 · Critical
Exploitability 6/34 · Minimal
Exposure 5/34 · Minimal