vLLM Denial of Service via the best_of parameter

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS 4.0

6.9 · CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N · score source

EPSS

• CVE-2024-8939: 0.23% estimated exploitation activity in the next 30 days; percentile 14.27 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

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. 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.

Published by the source

17 Sep 2024, 18:33 UTC

Last modified by the source

7 Aug 2026, 08:12 UTC

Source last checked

26 Oct 2026, 13:17 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-wc36-9694-f9rf

2. Revision 2 · amended · 25 Oct 2026

   Reviewed OSV alias/range/CVSS4 correction; package source scopes and original publication preserved. No customer finding resolved.

3. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-wc36-9694-f9rf

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2024-8939

Advisory: vLLM Denial of Service via the best_of parameter
IDs: CVE-2024-8939, GHSA-wc36-9694-f9rf
Record: https://patchnext.com/advisories/cve-2024-8939 (revision 3, source checked 26 Oct 2026, 13:17 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.9)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor response not established. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected <= 0.5.0.post1

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
No complete vendor fix is recorded. Follow the primary source's mitigation guidance and check this record again before closing anything.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-wc36-9694-f9rf (OSV record GHSA-wc36-9694-f9rf lists affected ranges: PyPI vllm >=0 <=0.5.0.post1)
- Verified: https://github.com/advisories/GHSA-wc36-9694-f9rf (GitHub-reviewed advisory GHSA-wc36-9694-f9rf lists affected ranges: PyPI vllm >=0 <=0.5.0.post1)

Commands are suggestions: review each one before running it.