pentestkit: Autonomous Multi-Agent Penetration Testing Framework Powered by LLMs

pentestkit is an autonomous, multi-agent penetration testing framework built on the Claude Agent SDK and powered by Kimi K3. It orchestrates specialized agents to plan attacks, exploit vulnerabilities with required proof, calculate CVSS v3.1 scores, and generate client-ready reports, achieving a 100% solve rate (104/104) on the XBOW validation benchmarks.

Demonstrates the frontier of autonomous LLM agents in real-world offensive security, bridging end-to-end vulnerability discovery, rigorous proof-of-exploit verification, and automated reporting.