SamBleed/ozy ? reverse-engineered prompt

Reverse engineered prompt

Build me a Go based tool that works like an autonomous bug bounty helper. I want to give it a target program and have it keep track of the scope, run recon against targets through a remote Kali machine over SSH, scan for issues, and save everything in SQLite so it remembers what it already found. It should be able to run continuously, detect changes over time, and keep a clear list of assets, findings, and investigation notes.

I also want an MCP server so I can control it from Claude or another AI assistant with simple commands like starting a hunt, checking status, adding findings, and generating a report. Please make it support a background daemon mode, use NATS for internal messaging if needed, and include useful tools for deeper scans, JS endpoint discovery, IDOR testing, and exporting results in a format that is easy to review later.

If anything is unclear, look up current docs online and keep the workflow practical.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab