GHSA-98f3-hwg4-4rf7 is a medium-severity (CVSS 5.3) CWE-404 vulnerability in vllm. No vendor fix is recorded yet; mitigation options are listed below.
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 GHSA-98f3-hwg4-4rf7.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
How urgent is this, really
GHSA-98f3-hwg4-4rf7 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.
Where this sits among everything scored
Of 384,534 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.
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 vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used. The pull request to fix this issue awaits acceptance.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | all versions | No fix |
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.
Remediation status
No patched version of vllm has shipped for GHSA-98f3-hwg4-4rf7 yet. Where your build allows, override or pin the dependency away from the vulnerable range, and apply any maintainer-recommended mitigation.
Mitigate without a patch
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 Moderate-severity denial of service flaw in the vllm OpenAI-compatible Serving Path, as deployed in Red Hat AI Inference Server, Red Hat OpenShift AI, and Red Hat Enterprise Linux AI, allows a remote attacker to disrupt service availability. The vulnerability specifically impacts the ability of the vllm service…
To mitigate this issue, restrict network access to the vllm OpenAI-compatible Serving Path to only trusted clients and networks. Implement firewall rules to limit exposure of the service to the public internet or untrusted internal networks.Source: Red Hat security advisory for GHSA-98f3-hwg4-4rf7 (CC BY 4.0)
Frequently Asked Questions
Is GHSA-98f3-hwg4-4rf7 in your dependencies?
Find it across PyPI, including transitive dependencies.