~ / search / GHSA-wc36-9694-f9rf

GHSA-wc36-9694-f9rf

vLLM Denial of Service via the best_of parameter

Source: GitHub Advisory Database (reviewed) Moderate CVE-2024-8939

Packages

EcosystemPackageAffectedFixed in
PyPI vllm <= 0.5.0.post1 no fix listed

Details

As written in the advisory (Markdown source, shown as plain text).

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

External links from the advisory. They lead to third-party sites.