Bug 2312782 (CVE-2024-8939)

Summary: CVE-2024-8939 vllm: Denials of Service in vllm JSON web API
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: unspecifiedCC: jeder
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc 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.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2024-09-17 08:14:17 UTC 
An improper timeout handling vulnerability exists in the ilab model serve component, which wraps the vllm JSON web API for interaction with a Large Language Model (LLM). When processing completion requests, the API accepts a parameter best_of that can cause excessive processing time if set to a large value. This improper handling can lead to a Denial of Service (DoS), making the API unresponsive to legitimate users. The issue primarily affects instances where the API is exposed beyond localhost.