CVE-2025-29783

CRITICAL

9.0

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.

CVE Details

CVSS v3.1 Score9.0

SeverityCRITICAL

CVSS VectorCVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Attack VectorADJACENT_NETWORK

ComplexityLOW

Privileges RequiredLOW

User InteractionNONE

Published3/19/2025

Last Modified7/1/2025

Sourcenvd

Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-502

References

https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/14228(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.