CVE-2024-8939 Vllm: denials of service in vllm json web api
An attacker can cause a Denial of Service in the vllm JSON web API by setting the best_of parameter to a large value, exhausting system resources.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2024-8939?
CVE-2024-8939 is a medium-severity denial of service vulnerability in Red Hat Enterprise Linux AI (RHEL AI), published on 17 Sep 2024. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Weakness: CWE-400
Which versions are affected by CVE-2024-8939?
3 open source packages ship an affected version, including vllm.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions to 0.5.0.post1 | None |
vllm PyPI | All versions to 0.5.0.post1 | None |
vllm PyPI | All versions to 0.5.0.post1 | None |
How do I fix CVE-2024-8939?
No fix has been published for CVE-2024-8939 yet. Limit exposure of the affected software until one is available.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2024-8939 being exploited?
There is no known exploitation of CVE-2024-8939 in the wild and no public exploit code.
Sources
Also known as CVE-2024-11040, GHSA-wc36-9694-f9rf, PYSEC-2026-2025.