title	AI Pentest API
emoji	🛡️
colorFrom	purple
colorTo	blue
sdk	docker
app_port	7860
pinned	false

🛡️ AI Pentest Scanner

An autonomous, AI-powered penetration testing tool that automates vulnerability discovery and reporting

📋 Table of Contents

• About
• Features
• Tech Stack
• Installation
• Usage
• Directory Structure
• License

📖 About

This folder contains the clean, standalone version of the AI Pentest Scanner. It is separated from legacy bot components for easier management.

The AI Pentest Scanner leverages multi-agent AI systems to perform comprehensive security scanning, including reconnaissance, vulnerability detection, and automated report generation.

✨ Features

• 🤖 Multi-Agent AI System - Specialized agents for different pentesting tasks
• 🎯 Automated Reconnaissance - Intelligent target enumeration and information gathering
• 🔍 Vulnerability Scanning - Automated detection of security weaknesses
• 📊 Auto-Report Generation - Professional reports in Markdown, HTML, JSON, and PDF
• 🖥️ Web UI - User-friendly interface for managing scans
• 💻 CLI Support - Run scans directly from terminal

🛠️ Tech Stack

Frontend:

• React (Vite)
• Tailwind CSS

Backend:

• Python Flask API
• Groq API (LLM)
• Gemini API (LLM)

Tools:

• Conda (Environment Management)
• npm (Package Manager)

📦 Installation

Prerequisites

• Python 3.8+
• Node.js 16+
• Conda

Setup

1. Clone the repository:

git clone https://github.com/samarth70/AI-Pentest-Scanner.git
cd AI-Pentest-Scanner

2. Install backend dependencies:

conda create -n agenticAi python=3.10
conda activate agenticAi
pip install -r requirements.txt

3. Install frontend dependencies:

cd frontend
npm install

4. Configure environment variables: Create a .env file in the root directory:

GROQ_API_KEY=your_groq_api_key
GEMINI_API_KEY=your_gemini_api_key

🚀 Usage

Option 1: Web Interface (Recommended)

1. Start the Backend API:

conda activate agenticAi
python api_server.py

The API will start at http://localhost:5000.

2. Start the Frontend: Open another terminal:

cd frontend
npm run dev

The UI will start at http://localhost:5173.

3. Access the Application: Open your browser and navigate to http://localhost:5173

Option 2: CLI Mode

Run scans directly from the terminal:

python main.py --target example.com

Additional CLI options:

python main.py --target example.com --scan-type full --output-format pdf

📚 Documentation

For detailed architecture, design decisions, and technical specifications, see:

• Architectural Documentation - Complete system architecture, agent design, and implementation details

📁 Directory Structure

AI-Pentest-Scanner/
├── api_server.py          # Flask backend for the web UI
├── main.py                # CLI entry point
├── agents/                # AI agents for different pentesting tasks
│   ├── recon_agent.py    # Reconnaissance agent
│   ├── vuln_agent.py     # Vulnerability scanning agent
│   └── report_agent.py   # Report generation agent
├── core/                  # Core configurations and utilities
│   ├── config.py         # Configuration settings
│   └── security.py       # Security utilities
├── frontend/              # Vite + React + Tailwind frontend
│   ├── src/              # React source code
│   ├── public/           # Static assets
│   └── package.json      # Frontend dependencies
├── reports/               # Generated scan results
│   ├── markdown/         # Markdown reports
│   ├── html/             # HTML reports
│   ├── json/             # JSON reports
│   └── pdf/              # PDF reports
├── .env                   # Environment variables (API keys)
└── requirements.txt       # Python dependencies

🔒 Security Note

This tool is intended for educational purposes and authorized security testing only. Always obtain proper authorization before scanning targets.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

👤 Author

Samarth Agarwal

• GitHub: @samarth70

Acknowledgments

• Groq for providing fast LLM inference
• Google Gemini for AI capabilities
• The open-source security community

---

⚠️ Disclaimer: Use responsibly and only on systems you own or have explicit permission to test.