FiredMosquito831

Bugbounty Cybersec AI Agent Resources — Security skill for Claude Code

Security community

Research archive & knowledge base for building an autonomous bug bounty / vulnerability discovery AI agent.

How to install Bugbounty Cybersec AI Agent Resources

This entry records only its repository, not the path inside it, so there is no exact command to give. Open FiredMosquito831/bugbounty-cybersec-ai-agent-resources and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Bugbounty Cybersec AI Agent Resources does

Research archive & knowledge base for building an autonomous bug bounty / vulnerability discovery AI agent. Curated repos, papers, tools, methodologies — Phase 1 (research) of an autonomous security agent project.

Alternatives in Security

/web3 Audit — Smart contract security audit using the 10-bug-class methodology 927 ★
Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★

README

Bug Bounty & Cybersec Resources for AI Agents

**This repository is the predecessor and active work-in-progress foundation for an autonomous bug bounty / vulnerability discovery AI agent.** It is a comprehensive, indexed research archive — the knowledge base that the agent will be built on.

What This Repo Is

A curated, read-only archive of **everything needed to build an autonomous AI agent that performs deep bug bounty hunting and vulnerability discovery** across web applications, APIs, networks, cloud infrastructure, binaries, smart contracts, and emerging attack surfaces.

This is **Phase 1 (Research & Curation)** of a larger project. The archive feeds directly into agent architecture design and implementation.

Why It Exists

Building an autonomous security agent requires grounding in:

Established methodology (OWASP, PTES, NIST, MITRE ATT&CK) — so the agent tests systematically
Verified research (Sailor, ELFuzz, ARACNE, NOVA) — architectures proven to work (30x improvement via composition)
Production tooling (36 repos) — real tools for the agent to invoke
Real-world patterns (681 disclosed reports, 2887 HackerOne cases) — learning from what actually gets paid
The Claude Code ecosystem (11,573 stars of agent blueprints) — building on existing patterns

What's Inside

Category	Count	Location
Cloned repos (read-only)	36	`repertoire/03_repos/` (see `REPO_MANIFEST.md` for URLs)
Academic/industry papers	17	`repertoire/01_papers/`
Catalogued sources with descriptions	1,216	`repertoire/_new_sources_full.tsv`
Books catalogued	55+	`repertoire/00_REPERTOIRE_INDEX.md`
YouTube channels	28	index
Conferences	12	index
Claude Code bug bounty repos	12 (11,573 stars)	`repertoire/03_repos/`

Start Here

repertoire/AUTONOMOUS_AGENT_CONTEXT.md — full context document (what, why, how, architecture insights, continuation guide). Read this first.
**`r