Vulnerability · Published Sep 17, 2024 · Assigned by redhat

CVE-2024-8939Vllm: denials of service in vllm json web api

Medium 6.2

In plain English

A medium-severity uncontrolled resource consumption in vllm. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 14% of all known vulnerabilities).

Severity (CVSS 3.1)6.2Medium

Exploit odds (30 days)0.2%top 85.7% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	no fix listed	GHSA-wc36-9694-f9rf
PyPI	vllm	no fix listed	PYSEC-2026-2025

Affected products (as reported)

Vendor	Product	Versions
	vllm	0 – before 0.5.0.post1
Red Hat	Red Hat Enterprise Linux AI (RHEL AI)	see references
Red Hat	Red Hat Enterprise Linux AI (RHEL AI)	see references

Weakness: CWE-400 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

https://access.redhat.com/security/cve/CVE-2024-8939 vdb-entry, x_refsource_REDHAT
RHBZ#2312782 issue-tracking, x_refsource_REDHAT