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.

Affected: PyPI: vllm

## Impacted Deployments

**Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.**

## Description

vLLM integration with mooncake is vaulnerable 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.

This is a similar to [GHSA - x3m8 - f7g5 - qhm7](https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7), the problem is in

https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179

Here [recv_pyobj()](https://github.com/zeromq/pyzmq/blob/453f00c5645a3bea40d79f53aa8c47d85038dc2d/zmq/sugar/socket.py#L961) Contains implicit `pickle.loads()`, which leads to potential RCE.

Affected: PyPI: vllm

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.