AI agent vulnerability · vLLM

CVE-2024-8939: vLLM Denial of Service via the best_of parameter

mediumCVSS 4.0 6.9 · 3.1 6.2GHSA-wc36-9694-f9rf

A vulnerability was found in the ilab model serve component, where improper handling of the bestof parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a bestof parameter to return the best completion from several options.

Published Sep 17, 2024

Affected packages

vllm

Ecosystem: PyPI
Affected: <= 0.5.0.post1
Fixed in: No patched version yet
Check: pip show vllm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More vLLM vulnerabilities

All vLLM entries