CVE-2026-9540: Denial of Service in vllm-project vllm
CVE-2026-9540 is a denial of service vulnerability in vllm-project vllm version 0.19.0. It involves an issue in the OpenAI-compatible Serving Path component that can be exploited remotely without authentication. A public exploit exists, but the fix is pending acceptance in a pull request.
AI Analysis
Technical Summary
The vulnerability in vllm-project vllm 0.19.0 affects the OpenAI-compatible Serving Path component, allowing an unauthenticated remote attacker to cause a denial of service. The exact processing flaw is unspecified. Although an exploit is publicly available, the vendor has not yet released an official fix, with a pull request awaiting acceptance.
Potential Impact
Successful exploitation results in denial of service, disrupting availability of the affected component. There is no indication of privilege escalation, data confidentiality, or integrity impact. The attack can be performed remotely without user interaction or privileges.
Mitigation Recommendations
No official fix or patch is currently available. A pull request addressing the issue is pending acceptance. Users should monitor the vendor's repository or advisory channels for the official patch. Until then, consider limiting exposure of the vulnerable service to untrusted networks to reduce risk.
CVE-2026-9540: Denial of Service in vllm-project vllm
Description
CVE-2026-9540 is a denial of service vulnerability in vllm-project vllm version 0.19.0. It involves an issue in the OpenAI-compatible Serving Path component that can be exploited remotely without authentication. A public exploit exists, but the fix is pending acceptance in a pull request.
CVSS v4.0
Score 6.9medium
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in vllm-project vllm 0.19.0 affects the OpenAI-compatible Serving Path component, allowing an unauthenticated remote attacker to cause a denial of service. The exact processing flaw is unspecified. Although an exploit is publicly available, the vendor has not yet released an official fix, with a pull request awaiting acceptance.
Potential Impact
Successful exploitation results in denial of service, disrupting availability of the affected component. There is no indication of privilege escalation, data confidentiality, or integrity impact. The attack can be performed remotely without user interaction or privileges.
Mitigation Recommendations
No official fix or patch is currently available. A pull request addressing the issue is pending acceptance. Users should monitor the vendor's repository or advisory channels for the official patch. Until then, consider limiting exposure of the vulnerable service to untrusted networks to reduce risk.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-05-26T05:44:55.913Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a15a0f6891d628fdc365f03
Added to database: 05/26/2026, 13:32:38 UTC
Last enriched: 06/30/2026, 23:52:39 UTC
Last updated: 07/31/2026, 19:23:00 UTC
Views: 174
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.