Skip to main content

Otodus - The Megalodon of Automated Pentesting with AI Agents

Project description

Otodus – The Megalodon of Automated Pentesting

License: MIT Python Framework

Author: AKM Korishee Apurbo (IMApurbo)
Version: 1.0.1
Release Date: December 2025


Overview

Otodus is a fully automated, AI-driven web application security testing platform designed for bug bounty hunters, security researchers, and red-team professionals.

It orchestrates intelligent AI agents to perform:

  • Reconnaissance
  • Deep endpoint crawling
  • Vulnerability classification
  • Payload generation & testing
  • True-positive verification

All delivered through a modern, real-time web dashboard.

Powered by GPT-4o-mini via Puter AI API – safe, accurate, and ethical by design.


Key Features

Automated Reconnaissance

  • Subdomain enumeration with subfinder + gobuster
  • Live host filtering with httpx
  • DNS & HTTP/HTTPS reachability validation

Intelligent Crawling

  • Deep endpoint discovery using CrawlerX
  • Automatic deduplication & normalization

AI-Driven Analysis

Four specialized agents:

  • Planner Agent – Creates targeted testing strategy
  • Classification Agent – Maps endpoints to vulnerability types
  • Exploit Agent – Generates safe, context-aware payloads
  • Verification Agent – Confirms findings with evidence

Web Dashboard

  • Real-time logs (AI reasoning, system, vulnerabilities)
  • Live vulnerability panel with severity badges
  • Scan progress bar & stage tracking
  • One-click Markdown report download

Safety & Control

  • Non-destructive payloads only
  • Manual scan stop at any time
  • Designed for authorized testing only

Installation

Requirements

  • Linux, macOS (or Windows)
  • Python 3.8+
  • Internet access (for AI API)

Step 1: Install External Recon Tools (optional but recommended)

# Subfinder & httpx (Go tools)
go install github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest
go install github.com/projectdiscovery/httpx/cmd/httpx@latest

# Gobuster
# Debian/Ubuntu
sudo apt install gobuster
# macOS
brew install gobuster
# Or use Docker images if preferred

Step 2: Install Otodus

pip install otodus

CrawlerX is automatically installed as a dependency.


Running Otodus

# Start the dashboard
otodus

Open your browser:

http://localhost:5000

Authentication

The tool uses Puter AI API (GPT-4o-mini).

The token is stored securely in your user config directory:

  • Linux/macOS: ~/.config/otodus/auth_token.txt
  • Windows: C:\Users\<username>\AppData\Roaming\otodus\auth_token.txt

Usage

  1. Enter target domain (e.g., testphp.vulnweb.com)
  2. Click Start Auto Scan
  3. Watch real-time progress, AI reasoning, and findings
  4. Download the final Markdown report when finished

Directory Structure (after install)

site-packages/otodus/
├── otodus/
│   ├── __init__.py
│   ├── otodus.py
│   └── prompts/              # Built-in prompt templates
│       ├── sql_injection.txt
│       ├── xss_reflected.txt
│       ├── idor.txt
│       └── ...
└── bounty_workspace/         # Created at runtime (current dir)
    ├── recon/
    ├── scans/
    ├── endpoints/
    ├── vulnerabilities/
    └── reports/

Customization

  • Add new vulnerability types by creating .txt files in your local prompts/ folder (overrides built-in prompts)
  • Modify scan limits in AgentOrchestrator.run()
  • Extend AI agents with custom logic

Dependencies

Python

  • Flask
  • requests
  • crawlerx
  • platformdirs (for secure config storage)

External (optional)

  • subfinder
  • gobuster
  • httpx

Legal & Ethical Notice

Authorized Use Only

This tool is intended strictly for:

  • Systems you own
  • Systems you have explicit written permission to test

Unauthorized testing is illegal and unethical.


⭐ Credits

Created by: IMApurbo


📃 License

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

otodus-1.0.1-py3-none-any.whl (47.6 kB view details)

Uploaded Python 3

File details

Details for the file otodus-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: otodus-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 47.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for otodus-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ea07aed2003567091febc3e48ce3e1a195719c8faa0e3c1de9aa8275beb7da61
MD5 819f6fb0d4ac0e0e5f4953d80ec883b9
BLAKE2b-256 48ed4997bc45206a8f8a007eee45d8c396bda5dacf7499e840634d4a6396c544

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page