offensive-security
10 repositories
Autonomous AI agents that hack and patch your app like a red team — Strix deploys autonomous AI agents that act like real attackers, running actual exploits to find and validate vulnerabilities in your application, then help fix them. It targets developers, security teams, and bug bounty hunters who want automated, agent-driven pentesting instead of manual testing.
An AI agent that pentests code and only reports proven exploits — Shannon is an open-source agent that reads your source code, maps attack paths, and actually executes exploits against web apps and APIs rather than just flagging suspected issues—no exploit, no report. Run it locally via npx for CI/CD or pre-production security checks; useful for appsec and devsecops teams wanting automated, evidence-based pentesting.
Self-hosted multi-agent AI system for automated penetration testing — PentAGI runs multiple autonomous AI agents, built with Go and a React frontend, to carry out penetration testing tasks end-to-end. It supports models like GPT and Anthropic, exposes a GraphQL API, and targets security researchers and ethical hackers wanting self-hosted, automated offensive security workflows.
Turning Claude Code Into a Scoped Bug-Hunting Operator — This Claude Code skill bundle adds 83 skills and 15 slash commands built from 681 disclosed HackerOne reports across 24 vulnerability classes, plus enterprise identity/infrastructure attack matrices and Burp MCP integration. It's aimed at bug hunters and red-teamers who want Claude to apply curated, cited detection patterns and chain templates rather than generic chat advice, tested on real engagements and public training targets like DVWA and Juice Shop.
T3MP3ST turns your existing coding agent into a self-hosted pentest engine — T3MP3ST is a multi-agent offensive-security harness that wraps around AI coding agents you already use (Claude Code, Codex, Ollama, etc.), running recon-exploit-report chains with no new API keys or cloud accounts. It claims 90.1% pass@1 on XBOW's 104-challenge suite, with all benchmark numbers reproducible via a single verify-claims command.
Ligolo-ng 0.8 adds a web UI, daemon mode, and multiplayer support — Ligolo-ng is a TUN-based tunneling tool for pentesters that avoids SOCKS/proxychains. Version 0.8 adds an API with a web interface for multiplayer use, a config file, daemon mode, auto-bind routing, and agent kill, with cross-platform support on Windows, Linux, macOS and BSD.
Open-source XBOW alternative: swarm agents that actually exploit bugs — Pentest Swarm AI pits dozens of ReAct-reasoning agents against APIs and web apps, chaining BOLA/IDOR, JWT forgery, mass assignment, SSRF and injection into scored attack paths rather than just scanning. Built in Go with native tools, it targets pentesters, bug bounty hunters, red teamers and researchers, and positions itself as an open alternative to XBOW.
ESP32-DIV HaleHound Edition for Cheap Yellow Display - Multi-protocol offensive security toolkit
A terminal agent that runs full pentest chains autonomously — PentestCode is a hard fork of OpenCode, repurposed from code editing into an autonomous terminal pentesting agent. It scans, enumerates, and attacks targets through coordinated multi-agent workflows with persistent engagement state, supporting 20+ LLM providers. Useful for operators who want an AI that runs the full attack chain, not just suggests commands.
Rust web framework that proves its own code and attacks itself — h5i combines an axum-based Rust web framework with Lean 4 formal verification and built-in red-teaming CLI tools. Developers can extract app logic into Lean proofs, mutation-test them, and separately run framework-independent recon, crawling and request-replay tools against any website for automated vulnerability discovery.