vllm 0.6.5-0.7.9 - Remote Code Execution via Unsafe Mooncake Deserialization
Title source: llmExploitation Summary
EIP tracks 1 public exploit for CVE-2025-29783. PoCs published by manus-use.
AI-analyzed exploit summary This repository contains functional exploit code for CVE-2025-32433, an Erlang OTP SSH vulnerability, demonstrating pre-authentication remote command execution via crafted SSH packets. The PoC includes a Dockerized vulnerable environment and a Python script to trigger the exploit.
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.
Exploits (1)
This repository contains functional exploit code for CVE-2025-32433, an Erlang OTP SSH vulnerability, demonstrating pre-authentication remote command execution via crafted SSH packets. The PoC includes a Dockerized vulnerable environment and a Python script to trigger the exploit.
References (3)
Scores
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H