Claude Bug Bounty — Plugin Guide

This repo is a Claude Code plugin for professional bug bounty hunting across HackerOne, Bugcrowd, Intigriti, and Immunefi.

What's Here

Skills (10 domains — load with /bug-bounty, /web2-recon, /token-scan, etc.)

Commands (33 slash commands)

Note: All commands are prefixed to avoid conflicts with Claude Code's built-in commands. /resume is a reserved Claude Code command — use /pickup to continue a previous hunt.

Agents (9 specialized agents)

• recon-agent — subdomain enum + live host discovery
• report-writer — generates H1/Bugcrowd/Immunefi reports
• validator — 4-gate checklist on a finding
• web3-auditor — smart contract bug class analysis
• chain-builder — builds A→B→C exploit chains
• autopilot — autonomous hunt loop (scope→recon→rank→hunt→validate→report)
• recon-ranker — attack surface ranking from recon output + memory
• token-auditor — fast meme coin/token rug pull and security analysis
• credential-hunter — orchestrates wordlist-gen + osint-employees + breach-check; HARD STOPS at spray for human go/no-go

Rules (always active)

• rules/hunting.md — 17 critical hunting rules
• rules/reporting.md — report quality rules

Tools (Python/shell — in tools/)

• bughunter/tools/hunt.py — master orchestrator
• bughunter/tools/recon_engine.sh — subdomain + URL discovery (now with optional nuclei phase)
• bughunter/tools/vuln_scanner.sh — XSS/SQLi/SSTI/MFA/SAML probe pipeline
• bughunter/tools/validate.py — 4-gate finding validator
• bughunter/tools/learn.py — CVE + disclosure intel
• bughunter/tools/intel_engine.py — on-demand intel with memory context
• bughunter/tools/scope_checker.py — deterministic scope safety checker
• bughunter/tools/scope_aggregator.sh — multi-platform scope pull (bbscope + bounty-targets-data)
• bughunter/tools/secrets_hunter.sh — trufflehog/noseyparker/gitleaks wrapper for FS/git/JS/GH-org
• bughunter/tools/takeover_scanner.sh — dnsReaper/subjack subdomain-takeover scanner
• bughunter/tools/cloud_recon.sh — S3Scanner + cloud_enum + CloudFail wrapper
• bughunter/tools/param_discovery.sh — Arjun/x8 hidden-parameter discovery
• bughunter/tools/bypass_403.sh — byp4xx + built-in 403/401 bypass matrix
• bughunter/tools/cve_scan.sh — focused nuclei CVE-tag sweep + optional log4j-scan
• bughunter/tools/external_arsenal.sh — installed-tool registry (~50 tools); other scripts source this for _have <tool>
• bughunter/tools/cicd_scanner.sh — GitHub Actions workflow scanner (sisakulint wrapper, remote scan)
• bughunter/tools/token_scanner.py — automated token red flag scanner (EVM + Solana)
• bughunter/tools/wordlist_engine.sh — company-specific password wordlist generator (cewler + hashcat rules); requires --with-credential-attack
• bughunter/tools/osint_employees.sh — employee names + email patterns for spray prep (theHarvester + username-anarchy, opt-in CrossLinked); requires --with-credential-attack
• bughunter/tools/breach_checker.py — HIBP k-anonymity wordlist enrichment; ranks passwords by breach count (no API key, free)
• bughunter/tools/spray_orchestrator.sh — password spray with typed-hostname guard + lockout warning + audit log; modes: http-form / oauth / o365 / okta (TREVOR); requires --with-credential-attack for TREVOR modes
• bughunter/tools/graphql_audit.sh — 7-phase GraphQL audit: introspection + schema dump, graphw00f fingerprint, clairvoyance field discovery, batching DoS, alias bomb, gqlmap injection, graphql-cop checklist
• bughunter/tools/lead_board.py — persistent per-target lead ledger that routes every recon observation to the right hunt-* skill and tracks its status so no lead is forgotten (memory/leads/<target>.jsonl). ingest parses recon output and routes 30+ signal types (IDOR/SSRF/GraphQL/OAuth/SAML/LLM/source-leak/tech-stack/nuclei) to skills; show lists untouched-first and flags stale high-priority leads; next returns the single top lead; touch marks a lead investigating/killed/reported (re-ingest preserves status). See Critical Rule 6.
• bughunter/tools/eol_check.py — EOL / lifecycle intel from endoflife.date (auto-run by hunt.py after recon)
• bughunter/tools/waf_encoder.py · waf_response_analyzer.py · multipart_mutator.py — WAF bypass + soft-block scoring + upload mutation
• bughunter/tools/cors_scanner.py — CORS misconfig scanner (origin-reflection / null / credentialed / suffix-prefix regex / scheme-downgrade); pure classifier, no deps
• bughunter/tools/crlf_scanner.py — CRLF / response-splitting + host-header injection with Set-Cookie canary detection (encoded + UTF-8 bypass variants)
• bughunter/tools/nosqli_scanner.py — NoSQL injection (operator auth-bypass, bracket-syntax, $where time-based blind) with differential + timing classifier
• bughunter/tools/jwt_scanner.py — offline JWT toolkit: alg:none forgery, RS256→HS256 confusion, HS256 secret crack, static claim analysis (pure stdlib)
• bughunter/tools/oob_listener.py — out-of-band orchestrator wrapping interactsh-client; payloads + correlation for blind SSRF/XXE/SQLi/RCE/Log4Shell
• bughunter/tools/llm_redteam.py — LLM red-team corpus runner (prompt-injection/jailbreak/system-prompt-leak/exfil/indirect/guardrail-bypass) with canary detection
• bughunter/tools/poc_bundler.py — PoC evidence bundler (capture live via SSRF-guarded safe_http, or from-request offline from a saved/Burp request). Emits request.http, response.http, repro.sh (curl), evidence.har (HAR 1.2), optional screenshot.png, evidence.md (report-ready), and bundle.json (manifest + response SHA-256) under findings/<target>-<class>/evidence/<id>/. Secrets redacted by default (repro.sh uses $ENV placeholders); refuses PUT/DELETE/PATCH without --confirm-unsafe. See /poc.
• bughunter/tools/hunt_dashboard.py — local web Hunt Dashboard (serve/export); reads memory/leads/, recon/, findings/, reports/, galleries, and hunt-memory/ into one live view. Pure stdlib, binds to 127.0.0.1, HTML-escapes all recon-derived data, path-traversal-guarded /file endpoint. Distinct from bughunter/tools/dashboard.py (the in-terminal ANSI progress TUI). See /dashboard.
• bughunter/tools/verifier.py — the report gate (prove-or-suppress). Independently re-derives a finding from its poc_bundler bundle (re-sends via SSRF-guarded safe_http with an initial-host guard, checks a confirmation marker in the fresh response headers+body) and decides reportability: PROVEN only if the marker was in the original response AND is still present now; else REFUTED/UNPROVEN/INCONCLUSIVE → suppressed. Records the re-fetched response's SHA + status. decide() is a pure, total policy function; only PROVEN ships. Writes verification.json; check/sweep; --require-proof exits non-zero for gating; unsafe methods never re-fired without --confirm-unsafe; secrets read from env only. Reuses only merged code (poc_bundler). See /verify.
• bughunter/tools/oracle.py — self-learning lead/finding prioritizer. Trains a smoothed Naive-Bayes log-odds model on journal.jsonl outcomes (confirmed/rejected + payout/severity/vuln-class/endpoint/tech features) to score P(lead becomes a real finding), replacing the static regex priority with a data-driven, per-feature-explainable rank. Cold-start prior blends toward the learned model as evidence grows; eval runs leave-one-out CV against the prior + majority baselines to prove lift. train / eval / rank <target> (reuses lead_board) / score. Pure-stdlib, deterministic, read-only. See /oracle.
• Full catalogue: bughunter/tools/README.md (~50 tools). hunt.py auto-ingests leads after recon (--graphql / --cve-hunt / --skip-leads flags).

External tool references

• wordlists/REFERENCES.md — pointers to SecLists / OneListForAll / fuzz4bounty / PayloadsAllTheThings
• skills/security-arsenal/REFERENCES.md — methodology, writeup archives, dorks, key-verification, AI-security skill repos
• skills/security-arsenal/METHODOLOGY_CHEATSHEET.md — per-vuln quick-check tables distilled from HowToHunt + HolyTips + AllAboutBugBounty + KingOfBugBountyTips

MCP Integrations (in mcp/)

• mcp/burp-mcp-client/ — Burp Suite proxy integration
• mcp/hackerone-mcp/ — HackerOne public API (Hacktivity, program stats, policy)

Hunt Memory (in memory/)

• memory/pattern_db.py — cross-target pattern learning
• memory/audit_log.py — request audit log, rate limiter, circuit breaker
• memory/rotation.py — size-based JSONL rotation (10MB cap, keep 3 backups), auto-fired on append
• memory/schemas.py — schema validation for all data

Start Here

claude
# /recon target.com
# /hunt target.com
# /validate   (after finding something)
# /report     (after validation passes)

Install Skills

chmod +x install.sh && ./install.sh

Critical Rules (Always Active)

1. READ FULL SCOPE before touching any asset
2. NEVER hunt theoretical bugs — "Can attacker do this RIGHT NOW?"
3. Run 7-Question Gate BEFORE writing any report
4. KILL weak findings fast — N/A hurts your validity ratio
5. 5-minute rule — nothing after 5 min = move on
6. LEAD BOARD — never lose a lead. After recon, run lead_board.py ingest <target> + show, and route each finding to its hunt-* skill in plain language ("GraphQL endpoint → hunt-graphql"). When starting/killing/reporting a lead, touch its status. The hunter focuses on one lead at a time; the board remembers the rest so none is forgotten. Surface stale high-priority leads unprompted.