CVE-2025-29783

March 19, 2025, 4:15 p.m.

10.0
Critical

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.

Product(s) Impacted

Vendor Product Versions
*
  • Vllm
  • 0.8.0

Weaknesses

Common security weaknesses mapped to this vulnerability.

CWE-502
Deserialization of Untrusted Data
The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid.

*CPE(s)

Affected systems and software identified for this CVE.

Type Vendor Product Version Update Edition Language Software Edition Target Software Target Hardware Other Information
a / vllm 0.8.0 / / / / / / /

CVSS Score

10.0 / 10

CVSS Data - 3.1

  • Attack Vector: NETWORK
  • Attack Complexity: LOW
  • Privileges Required: NONE
  • Scope: CHANGED
  • Confidentiality Impact: HIGH
  • Integrity Impact: HIGH
  • Availability Impact: HIGH
  • CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

    View Vector String

Timeline

Published: March 19, 2025, 4:15 p.m.
Last Modified: March 19, 2025, 4:15 p.m.

Status : Awaiting Analysis

CVE has been recently published to the CVE List and has been received by the NVD.

More info

Source

security-advisories@github.com

*Disclaimer: Some vulnerabilities do not have an associated CPE. To enhance the data, we use AI to infer CPEs based on CVE details. This is an automated process and might not always be accurate.