Lucene search
+L

vLLM: Completion prompt lists fan out into unbounded engine requests

🗓️ 19 Aug 2026 11:56:26Reported by Python Packaging AdvisoryType 
pypa
 pypa
🔗 github.com👁 8 Views

vLLM /v1/completions accepts unbounded list prompts, creating one engine generator per element to exhaust server resources.

Related
Detection
Refs

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

19 Aug 2026 12:16Current
5.9Medium risk
Vulners AI Score5.9
CVSS 3.16.5
EPSS0.00388
8