← Discover
Discover · GitHub · VulnClaw↑ +129 today

Automatic penetration testing with artificial intelligence

VulnClaw automates penetration testing processes using AI agents and the Model Context Protocol toolchain. The tool processes natural language commands and performs end-to-end information collection, vulnerability scanning, exploitation and reporting steps.

Updates

  • August 9, 2026: Stars 2,575 → 2,646, latest release v0.3.8 (August 9, 2026).
  • August 6, 2026: Stars 2,425 → 2,575, latest release v0.3.7 (August 4, 2026).
  • August 2, 2026: Stars 1,313 → 2,425, latest release v0.3.6 (July 25, 2026).

What you get

  • End-to-end penetration testing with natural language commands
  • Targeted autonomous security scanning
  • Automatic reporting and Python PoC generation

Installation

Installation via PyPI
pip install vulnclaw
Installation from source code
git clone https://github.com/Unclecheng-li/VulnClaw.git
cd VulnClaw
pip install -e .

Running it

Quick start
vulnclaw
Targeted scanning
vulnclaw run <target>

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

You are a penetration tester. Using the VulnClaw tool, collect information on the target system, perform vulnerability scanning and exploitation steps. Use the target-oriented solve engine while performing the operations, verify your findings and create a structured report and Python-based PoC code at the end of the process. At each stage, proceed based on the real data you obtain and avoid assumptions.

Related dictionary terms

Who it is forIt is for security researchers and penetration testers who want to automate their penetration testing processes.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-30: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.