awarexone/Agentic-Bug-Hunter

What it solves

Agentic Bug Hunter automates the bug bounty hunting process, moving from reconnaissance to final reporting. It eliminates the manual effort of mapping attack surfaces, testing for vulnerabilities, and drafting submission-ready reports for platforms like HackerOne and Bugcrowd.

How it works

The tool operates as an AI-powered research engine that can be used as a standalone CLI, a Claude Code plugin, or via the Model Context Protocol (MCP) for other AI agents. It integrates with external security tools (such as subfinder, httpx, nuclei, and nmap) to perform reconnaissance and vulnerability scanning. An AI agent then analyzes these results to hunt for flaws like IDOR, SSRF, and SQLi, validates findings through a "7-Question Gate" to filter out weak results, and generates professional reports.

Who it’s for

Security researchers, bug bounty hunters, and penetration testers who want to automate the discovery and reporting of real, reportable vulnerabilities.

Highlights

• End-to-End Automation: Handles the full loop from scoping and reconnaissance to validation and reporting.
• Flexible AI Integration: Supports a wide range of providers including local (Ollama), fast cloud (Groq, DeepSeek), and multi-model gateways (Fluxion, OpenRouter).
• Cros-Platform Access: Available as a standalone CLI, a Claude Code plugin, or an MCP server for agents like Cursor.
• Extensive Toolset: Includes specialized commands for cloud recon, secret hunting, 403 bypasses, and JWT scanning.