Critical severity · published Apr 30, 2025
CVE-2025-32444
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs
9.8
CVSS
1.8%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)1.8% · higher than 78% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
Vllm · Vllm
0.6.5 before 0.8.5 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-32444
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-32444
Product
https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179
Patch
https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c
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
More from Vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2025-47277
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache…