CVE-2024-8768 Vllm: a completions api request with an empty prompt will crash the vllm api server.
An attacker can crash the vLLM API server by sending a completions request with an empty prompt, causing a denial of service.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2024-8768?
CVE-2024-8768 is a high-severity denial of service vulnerability in Red Hat Enterprise Linux AI (RHEL AI), published on 17 Sep 2024. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service.
Weakness: CWE-617
Which versions are affected by CVE-2024-8768?
3 open source packages ship an affected version, including vllm.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.5.5 |
vllm PyPI | All versions | 0.5.5 |
vllm PyPI | All versions | 0.5.5 |
How do I fix CVE-2024-8768?
Upgrade vllm to 0.5.5 or later.
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-2024-8768 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2024-8768 exists.
Sources
Also known as GHSA-w2r7-9579-27hf, PYSEC-2026-2024.