An advanced AI-driven vulnerability scanner and penetration testing tool that integrates multiple AI providers (OpenAI, Grok, OLLAMA, Claude) with comprehensive security testing modules for automated bug hunting, intelligent payload generation, and professional reporting.

• Multi-AI Provider Support: Dynamic switching between OpenAI, Grok, OLLAMA, and Claude
• Intelligent Payload Generation: AI-powered, CVE-aware, context-sensitive payloads
• Comprehensive Scanning: 45+ attack methods with framework-specific tests
• Advanced Reconnaissance: Passive OSINT, DNS enumeration, subdomain discovery
• Professional Reporting: PDF/HTML/JSON reports with OSINT intelligence and executive summaries
• Collaborative Scanning: Team-based distributed scanning with session management
• Custom Plugin System: Extend Deep Eye with your own vulnerability scanners
• Multi-Channel Notifications: Real-time alerts via Email, Slack, and Discord

• SQL Injection (Error-based, Blind, Time-based)
• Cross-Site Scripting (XSS)
• Command Injection
• SSRF (Server-Side Request Forgery)
• XXE (XML External Entity)
• Path Traversal
• CSRF (Cross-Site Request Forgery)
• Open Redirect
• CORS Misconfiguration
• Security Headers Analysis

• Local File Inclusion (LFI)
• Remote File Inclusion (RFI)
• Server-Side Template Injection (SSTI)
• CRLF Injection
• Host Header Injection
• LDAP Injection
• XML Injection
• Insecure Deserialization
• Authentication Bypass
• Information Disclosure
• Sensitive Data Exposure
• JWT Vulnerabilities
• Broken Authentication

• API Security Testing (OWASP API Top 10 2023)
• GraphQL Security (Introspection, Depth limits, Batch attacks)
• Business Logic Flaws (Price manipulation, Workflow bypass, Race conditions)
• Authentication Testing (Session management, JWT, OAuth, MFA bypass)
• File Upload Vulnerabilities (Unrestricted upload, Path traversal, Type bypass)
• Collaborative Scanning (Team-based distributed scanning)

• WebSocket Testing (Origin validation, Auth, Injection, DoS protection)
• ML-Based Anomaly Detection (Behavioral analysis, Pattern recognition)
• Interactive HTML Reports (Charts, Filtering, Real-time search)
• Enhanced OSINT (Google dorking, Breach databases, CT logs, GitHub/Pastebin)
• Advanced Payload Obfuscation (11+ techniques for WAF bypass)

• Custom Plugin System (Extend with your own scanners)
• Multi-Channel Notifications (Email, Slack, Discord alerts)
• Enhanced OSINT Reporting (Reconnaissance data in all reports)

And 17+ more attack vectors

• Python 3.8 or higher
• pip package manager
• API keys for AI providers (at least one):
  • OpenAI API Key
  • Anthropic (Claude) API Key
  • Grok API Key
  • OLLAMA (local installation)

Windows:

.\scripts\install.ps1

Linux/Mac:

chmod +x scripts/install.sh
./scripts/install.sh

1. Clone the repository:

git clone https://github.com/zakirkun/deep-eye.git
cd deep-eye

2. Install dependencies:

pip install -r requirements.txt

3. Configure AI providers:

cp config/config.example.yaml config/config.yaml
# Edit config.yaml with your API keys

# Scan with target from CLI
python deep_eye.py -u https://example.com

# Scan with configuration file
python deep_eye.py -c myconfig.yaml

# Verbose mode
python deep_eye.py -u https://example.com -v

All scan options are configured in config/config.yaml:

scanner:
  target_url: "https://example.com"  # Default target
  ai_provider: "openai"               # AI provider
  default_depth: 2                    # Crawl depth
  default_threads: 5                  # Thread count
  enable_recon: true                  # Enable reconnaissance
  full_scan: false                    # Full/quick scan mode
  proxy: ""                           # Proxy settings
  custom_headers: {}                  # Custom headers

reporting:
  enabled: true                       # Auto-generate reports
  output_directory: "reports"         # Report directory
  default_format: "html"              # Report format

Then run:

python deep_eye.py

-u, --url              Target URL (overrides config)
-c, --config           Configuration file path (default: config/config.yaml)
-v, --verbose          Enable verbose output
--version              Show version and exit
--no-banner            Disable banner display

Note: All scanning options (depth, threads, AI provider, scan mode, proxy, etc.) are now configured in config.yaml for better management and repeatability.

deep-eye/
├── core/                      # Core scanning engine
├── ai_providers/              # AI provider integrations
├── modules/                   # Security testing modules
├── utils/                     # Utility functions
├── config/                    # Configuration files
├── templates/                 # Report templates
├── examples/                  # Usage examples
├── scripts/                   # Installation scripts
├── docs/                      # Documentation
├── deep_eye.py               # Main entry point
├── setup.py                  # Package setup
└── requirements.txt          # Dependencies

For detailed structure, see docs/ARCHITECTURE.md

Issue: PDF generation errors on Windows (WeasyPrint library issues)

Solution: The tool now uses ReportLab (Windows-friendly) for PDF generation by default. If you encounter any issues:

1. Ensure ReportLab is installed:

pip install reportlab>=4.0.0

2. If PDF generation fails, the tool will automatically fall back to HTML format.

3. For advanced HTML-to-PDF conversion (optional), you can install additional tools, but it's not required.

AI Provider Connection Errors

• Verify your API keys in config/config.yaml
• Check your internet connection
• Ensure API key has sufficient credits

Scanning Errors

• Verify target URL is accessible
• Check if target has rate limiting or WAF
• Try reducing thread count with -t option

IMPORTANT: Deep Eye is designed for authorized security testing only.

• Only use on systems you own or have explicit permission to test
• Unauthorized access to computer systems is illegal
• Users are responsible for complying with all applicable laws
• The developers assume no liability for misuse

Contributions are welcome! Please feel free to submit a Pull Request.

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

• Quick Start Guide - Get started quickly
• Architecture - System design and structure
• Testing Guide - Testing procedures
• Contributing - How to contribute
• Changelog - Version history

• OpenAI for GPT models
• Anthropic for Claude
• OWASP for security testing methodologies
• The security research community

For questions or support, please open an issue on GitHub.

⚠️ Use Responsibly | 🔒 Test Ethically | 💡 Learn Continuously