bug-bounty (Claude-BugHunter)
End-to-end bug bounty master workflow: recon, learn, hunt, validate, and report — one skill for everything.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for bug-bounty (Claude-BugHunter), derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
The master skill of the Claude-BugHunter bundle: a full Recon -> Learn -> Hunt -> Validate -> Report pipeline covering subdomain enumeration, source-code audit, vulnerability hunting across dozens of classes (IDOR, SSRF, XSS, SQLi, XXE, OAuth, SSTI, cloud misconfig), LLM/AI security testing, A-to-B bug chaining, and CVSS/PoC reporting. Real security surface: it orchestrates offensive tooling and grep audits against live targets.
Key features and capabilities
- Full recon-to-report offensive pipeline
- Dispatches to 60+ class-specific hunting sub-skills
- LLM/AI security testing and bug-chaining tables
Use cases
- Kick off a new bug-bounty target end to end
- Author a validated vulnerability report