
VulnClaw
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。

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。

Linux privesc enumerator that confirms exploitability and gives you the exact root shell command - no GTFOBins searching. MCP server + AI-agent…

Security portfolio of original responsible-disclosure findings, CTF and lab write-ups, methodology notes, and purpose-built pentest tooling covering…

Self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Plugin-based, multi-provider LLM support with local…

Self-hosted OWASP CTF kit: one box, one free GitHub org, no cloud dependencies

AI-driven penetration testing agent that connects to a Kali box, autonomously runs security tools, analyzes results, and iterates through…

C++ challenge repository exploring Control Flow Guard (CFG) bypass techniques for Windows binary exploitation research.

SecDim Challenge Builder repro inspired by CVE-2026-88861: AAL1 MFA bypass at privileged credential boundary

Python proof-of-concept for CVE-2022-25765, a command injection vulnerability in pdfkit, enabling remote code execution via crafted PDF generation.

Proof-of-concept exploit for an authentication bypass in marimo's terminal WebSocket endpoint, enabling unauthenticated command execution in versions…

An implementation of a vulnerable MCP server using mcp-go

React Server Components 远程代码执行漏洞(CVE-2025-55182)

Step-by-step walkthrough of exploiting CVE-2025-53770 (ToolShell) in a LetsDefend lab, covering RCE, web shell deployment, and incident response…

Automated exploitation tool for CVE-2025-55182 (React/Next.js RCE) with command execution, outbound detection, interactive reverse shell, and…

Self-contained security training lab reproducing CVE-2026-20253 (Splunk Enterprise unauthenticated RCE). Provides a Docker-based environment to…

PoC for CVE-2025-55319

Exploitation de CVE-2022-22980