Skip to content

[GitHub Trending] Unclecheng-li/VulnClaw

7.6 relevance
Score Breakdown
technical depth
8
novelty
8
actionability
8
community
6
strategic
5
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

AI Agent + MCP for penetration testing, strong match with agent orchestration.

AI/ML github.com
基于 AI Agent + MCP 工具链 + 渗透 Skill 编排, 配合大语言模型, 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。 - Unclecheng-li/VulnClaw
Summary

VulnClaw is an open-source CLI tool that uses LLM agents and MCP toolchains to automate penetration testing from information gathering to report generation. Its core innovation replaces fixed-round workflows with a goal-driven solver engine that models penetration as a state-space search over Facts and Intents, preventing redundant loops. An evidence-level anti-hallucination gate validates claimed findings against actual tool outputs, enabling reliable operation even with weaker models.

Author

Unclecheng-li