Lucene search
K

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

🗓️ 21 Aug 2025 14:46:51Reported by GitHub Advisory DatabaseType 
github
 github
🔗 github.com👁 15 Views

vLLM Qwen3-Coder parser unsafe eval enables authenticated users to run remote code via tool calls.

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