Python MIT

ai4eh

AI for Ethical Hacking - Workshop

E

ethiack

Dernière activité 28 nov. 2025
ethiack/ai4eh

298

étoiles

51

forks

0

issues ouvertes

hackbothackingllmmcpnlpreconsecurity

Ce README est souvent en anglais.


logo

AI for Ethical Hacking

This repository contains the workshop guide, educational tools and scripts for learning how AI can be applied in offensive security.

🎯 Overview

The AI4EH workshop demonstrates some practical applications of AI in security, including:

  • AI Reconnaissance - Generate contextual subdomain wordlists and automate target enumeration
  • Intelligent Screenshot Analysis - Use neural networks and multimodal LLMs to classify web apps
  • Smart Content Discovery - Create custom fuzzing wordlists based on application context
  • Automated Exploit Generation - Explore nuclei AI template generation
  • Hackbots - Play with CAI agents for vulnerability discovery
  • MCP Integrations - Connect AI assistants to security tools like Burp Suite, Ghidra and more

🚀 Quick Start

  1. Build the container:

    chmod +x build_image.sh
    ./build_image.sh
  2. Run the environment:

    chmod +x run_image.sh
    ./run_image.sh

Or simply use the pre-built image:

docker run --rm -it --env-file env_file ethiack/ai4eh:latest

🛠️ Tools & Components

Core Scripts

  • llm_screenshot_classifier.py - Multimodal AI for categorizing web application screenshots
  • scrape.py - Web scraping with analysis
  • nlp.py - NLP utility for keyword extraction and text analysis
  • cai_custom_xss_tool_with_notify.py - AI agent example with a simple custom tool for notifications

Included Security Tools

The Docker environment includes popular tools:

  • LLM - Access LLMs from the command-line
  • Nuclei - Fast, customizable vulnerability scanner
  • FFUF - Fast web fuzzer
  • FFUFAI - AI-powered ffuf wrapper
  • Subfinder - Fast passive subdomain enumeration tool
  • HTTPx - Multi-purpose HTTP toolkit
  • Notify - Assistance package for sending notifications
  • EyeBaller - Convolutional neural network for analyzing pentest screenshots
  • PureDNS - Fast domain resolver and subdomain bruteforcing tool

📋 Prerequisites

  • Docker
  • API keys for AI services (Google Gemini, OpenAI, etc.)
  • Basic understanding of security concepts

⚙️ Configuration

Create an env_file with your API credentials:

OPENAI_API_KEY=your_openai_key_here
GEMINI_API_KEY=your_gemini_key_here
...

🎓 Educational Use Only

This content is designed for:

  • ✅ Learning AI applications in offensive security
  • ✅ Educational vulnerability research
  • ✅ Authorized penetration testing
  • ✅ CTF experiments

🤝 Contributing

This is an educational project. Feel free to:

  • Report issues or bugs
  • Suggest improvements to existing tools
  • Share educational use cases

📄 License

Educational use - always respect responsible disclosure and ethical hacking principles.


Disclaimer: This content is intended for educational purposes and authorized security testing only. Users are responsible for ensuring compliance with applicable laws and regulations.

Projets similaires

This repository is maintained by Omar Santos (@santosomar) and includes thousands of resources related to ethical hacking, bug bounties, digital forensics and incident response (DFIR), AI security, vulnerability research, exploit development, reverse engineering, and more. 🔥 Also check: https://hackertraining.org

Jupyter Notebookaiai-securityartificial-intelligence
TThe-Art-of-Hacking
29,6 k étoiles5,4 k

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

Pythonlarge-language-modelsllmpenetration-testing
Iipa-lab
1,2 k étoiles218

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Python0x4m4aiai-agents
00x4m4
12,2 k étoiles2,5 k