crítica
CVE-2025-32444
vllm: vLLM Vulnerable to Remote Code Execution via Mooncake Integration
En la Trivy database desde, como mínimo, el 24 oct 2026, 07:11 UTCNo consta cuándo entró antes de ese build.
Severidad por fuente
NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GHSA10.0CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Red Hat10.0CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
La etiqueta propia de Trivy es CRITICAL. Crítica según NVD, GHSA, Red Hat.
Descripción
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.
Paquetes afectados y versiones corregidas
| Fuente | Paquete | Corregido en |
|---|---|---|
| pip::GitHub Security Advisory pip | vllm | 0.8.5 |
Referencias
- https://access.redhat.com/security/cve/CVE-2025-32444
- 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
- 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
- https://nvd.nist.gov/vuln/detail/CVE-2025-32444