🛡️ PENTESTING – ML-Aided Cyber Vulnerability Scanner

An advanced toolkit for scanning, bypassing, and predicting system vulnerabilities using automation and machine learning.

---

🛠️ Built With

Python • Nmap • Bettercap • ARP-Scan • SQLMap • Nikto • Metasploit • XGBoost • Scikit-learn • Pandas • Tkinter

---

📑 Table of Contents

• 🔍 Overview
• 🚀 Getting Started
• ✅ Prerequisites
• 🛠️ Installation
• ▶️ Usage
• 📊 Output Format
• 🧠 Machine Learning Pipeline
• 🧪 Testing
• 📄 License
• 🔙 Return

---

🔍 Overview

Pentesting is a GUI-based cybersecurity suite that automates the process of network reconnaissance, vulnerability scanning, firewall evasion, and machine learning-based vulnerability prediction. It enables ethical hackers and security teams to streamline offensive security assessments with a unified toolkit.

✨ Key Features:

• 🔎 Network Reconnaissance using Nmap, Bettercap, and ARP-scan.
• 🔥 Firewall Bypass techniques for stealth scanning and evasion.
• 🧰 Modular Vulnerability Scanning via SQLMap, Nikto, and Metasploit.
• 🧠 Machine Learning Predictions on scan results using trained XGBoost & Isolation Forest models.
• 📁 Automated CSV Dataset Generation from scan results for analytics or training.

---

🚀 Getting Started

Clone the repository:

git clone https://github.com/yogambar/pentesting
cd pentesting

---

✅ Prerequisites

Ensure you have the following installed:

• Python 3.8+
• All tools in system PATH: Nmap, SQLMap, Bettercap, Metasploit, ARP-scan
• virtualenv or similar Python environment manager

---

🛠️ Installation

1. Create and activate a virtual environment:

python3 -m venv myenv
source myenv/bin/activate

2. Install all dependencies:

pip install -r setup/requirements.txt

---

▶️ Usage

Launch the GUI application:

python3 gui/gui.py

GUI Features:

• Scan Network → Discover live hosts on the network.
• Select Target IP → Choose any discovered IP for analysis.
• Bypass Firewall → Use stealth scan modes to evade defenses.
• Run All Scans → Execute Nmap, SQLMap, Nikto, and Metasploit on target.
• Run Single Tool → Choose a specific scanner manually.
• Save Scan Data → Aggregate and convert all JSON outputs into a structured CSV.
• Train Model → Train ML models using collected data.
• Predict Vulnerability → Predict target vulnerability using trained models.

---

📊 Output Format

Each scan outputs to:

data/scan_outputs/
├── nmap.json
├── sqlmap.json
├── nikto.json
├── metasploit.json

These are merged into dataset.csv for use in training or inference.

---

🧠 Machine Learning Pipeline

• Feature extraction via ml/feature_extractor.py
• Model training via model_trainer.py, producing:
  • xgboost_model.joblib
  • isolation_forest_model.joblib
  • label_encoders.joblib
  • scaler.joblib
• Prediction via predictor.py for new IPs

---

🧪 Testing

Custom test scripts are located in tests/ (if applicable). Basic testing can be performed by running:

pytest tests/

---

📄 License

This project is licensed under the MIT License. See LICENSE for more information.

---

🔙 Return

🔼 Back to Top