Claude Bug Bounty provides a full automated security testing pipeline: subdomain enumeration, DNS resolution, live host detection, URL crawling, and vulnerability scanning across 20 classes including SQLi, XSS, SSRF, IDOR, OAuth flaws, and LLM prompt injection. It validates findings through a strict gate to reduce false positives and generates submission-ready HTML reports for HackerOne, Bugcrowd, Intigriti, and Immunefi.
Claude Bug Bounty is an automated security testing toolkit that operates from the terminal. It provides a complete pipeline from reconnaissance through vulnerability scanning to report generation, supporting 20 vulnerability classes and multiple bug bounty platforms. It works as a Claude Code plugin or as a standalone CLI tool (bughunter).
The toolkit covers the full bug bounty workflow. Reconnaissance includes subdomain enumeration, DNS resolution, live host detection, and URL crawling. The scanning engine tests for 20 vulnerability classes including SQL injection, cross-site scripting, server-side request forgery, insecure direct object references, OAuth misconfigurations, GraphQL vulnerabilities, race conditions, and LLM prompt injection. A validation gate filters findings to reduce false positives before generating submission-ready reports.
Claude Bug Bounty is designed for security researchers participating in bug bounty programs on HackerOne, Bugcrowd, Intigriti, and Immunefi. It automates the repetitive parts of vulnerability hunting — reconnaissance, scanning across vulnerability classes, and report formatting — so researchers can focus on complex attack chains and manual testing. The persistent state feature makes it practical for long-running engagements across multiple targets.
This tool is intended for authorized security testing only. Always ensure you have explicit permission before testing any target. The tool supports multiple AI providers including Ollama for local/free operation, but the quality of vulnerability detection depends on the underlying model’s capabilities. Findings should be manually verified before submission to bug bounty platforms.
Claude Bug Bounty is for security researchers and bug bounty hunters who want to automate reconnaissance and initial vulnerability scanning. It is particularly useful for researchers working across multiple platforms and targets who need consistent recon workflows and standardized report formatting.
Builder.io's open-source framework for building agent-native applications — shared actions, SQL-backed state, identity, tools, skills, jobs, observability, and UI surfaces that all work together.
Persistent memory layer for AI coding agents — benchmark-backed (95.2% on LongMemEval-S), 92% fewer tokens per session vs full-context pasting, zero manual memory.add() calls.
Open-source AI pair programming tool that works in your terminal to edit code across your entire repository.