CVE-2025-29783

What it is

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.

At a glance

Exploitability

Can be exploited from the same network segment with a low-privilege account. High risk of data exposure, data tampering, service disruption.

Exploit odds

0.7% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2025-03-19 16:15 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-06-17 09:05 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.7% in the next 30 days (EPSS).
• Severity: 9.0 CRITICAL (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2025-03-19 16:15 UTC

Last modified

2026-06-17 09:05 UTC

Exploit probability

0.7% · EPSS, next 30 days

Weakness

CWE-502 · Unsafe deserialization

Record status

Analyzed

Affected

• Vllm < 0.8.0

Attack profile CVSS 3.1 · 9.0

Attack vector

Adjacent network

Complexity

Low

Privileges needed

Low

User interaction

None

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High

Is it in your code?

Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.

Read https://cve-list.com/agent/cve/CVE-2025-29783.md and follow it. Check whether this project is affected by CVE-2025-29783. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.

Copy as ticket · More options · Status badge