CVE-2024-8768 is a high-severity (CVSS 7.5) Reachable Assertion vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.
Vllm: a completions api request with an empty prompt will crash the vllm api server.
Exploitation Status
Proof-of-concept exploit code exists
- CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
Exploitation and automatability from CISA’s SSVC triage for CVE-2024-8768.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
How urgent is this, really
Where this sits among everything scored
Real-World Exposure
vllmReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
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.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | all versions | 0.5.5pip install --upgrade 'vllm==0.5.5' |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update vllm to 0.5.5 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2024-8768 is resolved across your whole dependency graph.
Workarounds
Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.
Fixing This On Your OS
If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.
This vulnerability can only be exploited when vLLM is serving GPT-2 models, other models are not affected by this issue. As this flaw allows remote users to cause a denial of service, it has been rated with an important severity.
Red Hat has investigated whether a possible mitigation exists for this issue, and has not been able to identify a practical example. Please update the affected package as soon as possible.Source: Red Hat security advisory for CVE-2024-8768 (CC BY 4.0)
Frequently Asked Questions
Is CVE-2024-8768 in your dependencies?
Find it across PyPI, including transitive dependencies.