vLLM Vulnerable to Remote Code Execution via Mooncake Integration
28Vexday Risk Score
Sin señal de explotación. Ningún artefacto público de explotación conocido hasta ahora.
ssvc Trackcvss 10epss 1.7%
probabilidad de explotación
1.7%top 26% de las CVE
explotación observada
noninguna fuente lo reporta
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:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Productos afectados
vllm-project · vllmReferencias
https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2chttps://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7