Vision Graph Vulnerability Detector

AI-powered real-time vulnerability detection for C, C++, and Java using Graph Neural Networks. Detect security flaws as you code!

🛡️ Features

Real-time Vulnerability Detection

• Buffer Overflow: Detects unsafe functions like strcpy, sprintf, gets
• SQL Injection: Identifies dynamic query construction vulnerabilities
• Command Injection: Spots dangerous system() calls
• Hardcoded Credentials: Finds embedded passwords and secrets
• Format String Vulnerabilities: Catches unsafe printf usage

VS Code Integration

• ✅ Real-time Analysis: Scans code as you type with 1-second debounce
• ✅ Native Diagnostics: Red underlines with hover tooltips
• ✅ Rich UI: Beautiful results panel with detailed explanations
• ✅ Command Palette: Easy access to analysis commands
• ✅ Status Bar: Shows analysis progress and issue count
• ✅ Multi-language: Supports C, C++, and Java

🚀 Quick Start

1. Install Extension: Search "Vision Graph" in VS Code Extensions
2. Install Python Dependencies:

   pip install flask flask-cors numpy scipy networkx
   

3. Open Supported File: Any .c, .cpp, .h, .hpp, or .java file
4. See Results: Vulnerabilities appear as red underlines

📋 Commands

Installation

Prerequisites

• Python 3.8 or higher
• pip package manager

Install Dependencies

1. Navigate to the vision_graph_backend directory:

   cd vision_graph_backend
   pip install -r requirements.txt
   

Install Extension

1. Open VS Code
2. Go to Extensions (Ctrl+Shift+X)
3. Install "Vision Graph Vulnerability Detector"
4. Or install from VSIX: code --install-extension vision-graph-extension-0.0.1.vsix

Usage

Commands

• Vision Graph: Analyze Current File - Analyze the currently open file
• Vision Graph: Analyze Workspace - Analyze all C/C++/Java files in workspace
• Vision Graph: Show Results Panel - Show detailed analysis results
• Vision Graph: Clear Results - Clear all diagnostics

Real-time Analysis

The extension automatically analyzes supported files when you:

• Type code (with 1-second debounce)
• Save files
• Open supported files

Configuration

Access settings via Ctrl+, and search for "Vision Graph":

{
  "visionGraph.pythonPath": "python3",
  "visionGraph.backendPort": 5001,
  "visionGraph.enableRealTime": true,
  "visionGraph.severityLevel": "medium"
}

Development

Building the Extension

cd vision-graph-extension
npm install
npm run compile

Running in Development

1. Open the vision-graph-extension folder in VS Code
2. Press F5 to launch Extension Development Host
3. The extension will be loaded in a new VS Code window

Packaging

npm install -g @vscode/vsce
vsce package

Architecture

┌─────────────────┐    HTTP/REST    ┌──────────────────┐
│   VS Code       │ ───────────────▶ │ Python Flask     │
│   Extension     │                 │ Backend Server   │
│   (TypeScript)  │ ◀─────────────── │ (Port 5001)      │
└─────────────────┘                 └──────────────────┘
        │                                    │
        ▼                                    ▼
┌─────────────────┐                 ┌──────────────────┐
│ VS Code         │                 │ Graph Neural     │
│ Diagnostics &   │                 │ Network Analysis │
│ UI Components   │                 │ (Simulated)      │
└─────────────────┘                 └──────────────────┘

Contributing

1. Fork the repository
2. Create a feature branch
3. Make changes
4. Add tests
5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

For issues and feature requests, please visit our GitHub repository.