URL Vulnerability Detection System

A browser extension that analyzes URLs and detects potential security risks such as SQL Injection (SQLi), Broken Access Control (BAC), and Security Misconfiguration using machine learning and rule-based techniques.

---

Overview

This project focuses on identifying whether a given URL is safe or vulnerable by analyzing patterns, request structures, and known threat indicators.

It provides:

• Risk classification (Low, Medium, High, Critical)
• Visual representation of vulnerabilities
• Real-time detection via a browser extension interface

---

Features

• URL risk analysis
• Risk score visualization (charts / metrics)
• Detection of:
  • SQL Injection (SQLi)
  • Broken Access Control (BAC)
  • Security Misconfiguration
• Browser extension popup interface
• Fast and lightweight predictions

---

Tech Stack

• Frontend: HTML, CSS, JavaScript
• Backend / Logic: Python
• Libraries Used:
  • Machine Learning (Scikit-learn)
  • Data Processing (Pandas, NumPy)
  • Visualization libraries
• Other Tools:
  • Browser Extension APIs

---

How It Works

1. User visits or inputs a URL
2. The system extracts relevant features from the URL
3. Features are processed and passed to the trained model
4. The model predicts the risk level
5. Results are displayed in the extension popup