---
id: 7521
title: "pentestkit: Autonomous Multi-Agent Penetration Testing Framework Powered by LLMs"
source_domain: github.com
source_url: "https://github.com/lordx64/pentestkit"
published_at: "2026-07-31T23:26:22Z"
tags: ["ai-security", "bug-bounty", "pentesting", "benchmark", "red-team", "llm", "cvss", "multi-agent", "claude-agent-sdk", "kimi"]
phying_url: "https://phying.com/item/7521"
lang: en
---

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

## Summary

An autonomous multi-agent pentest framework built on the Claude Agent SDK and powered by Kimi K3, achieving 104/104 (100%) on the XBOW benchmark with proven findings and CVSS v3.1 scoring.

## Why it matters

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.

## Intelligence Metadata

- **Sources:** github.com
- **Published:** 2026-07-31T23:26:22Z
- **Original:** https://github.com/lordx64/pentestkit
- **Phying News:** https://phying.com/item/7521