# elementalsouls/Claude-BugHunter

A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.

Repository: https://github.com/elementalsouls/Claude-BugHunter
Canonical: https://ross.abutalabs.com/products/claude-bughunter
Homepage: https://elementalsouls.github.io/Claude-BugHunter
Language: Python
License: MIT
License Family: permissive
Topics: ai-security, anthropic, application-security, bug-bounty, bugbounty, bugcrowd, claude, claude-code, claude-skills, ethical-hacking, hackerone, offensive-security, pentesting, red-team, security-tools, web-security
Last push: 2026-08-26T04:58:19+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 87, longevity 8
- inputs: {"age_days": 120, "days_push": 7, "days_rel": 89, "gap_med": 10, "n_releases_24m": 2}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3801, forks 588 (observed 2026-08-28T04:08:19.913734+00:00)

## What it is
A Claude Code skill bundle that turns Claude into a bug-hunting and red-team assistant, with 83 skills, 15 slash commands, and 681 disclosed-report patterns across 24 vulnerability classes. It includes enterprise attack matrices, triage validation gates, VRT severity mapping, and Burp MCP integration for authorized security engagements.

## Use cases
- run recon on an in-scope bug bounty target and rank attack surface
- hunt web vulnerabilities like XSS, SSRF, or IDOR using curated payload and bypass patterns
- assess enterprise platforms such as M365/Entra, Okta, or vCenter for known CVE chains
- validate and triage findings before submitting a HackerOne report
- generate client-facing red-team reports with proper evidence hygiene and PII redaction
- practice on training platforms like DVWA, OWASP Juice Shop, or Hacker101

## When to choose
- you use Claude Code for authorized bug bounty or red-team work and want curated methodology and payloads
- you need auditable, cited vulnerability patterns from disclosed HackerOne reports
- you want scope-aware validation gates and VRT-aligned severity mapping built into your workflow

## When to avoid
- you lack authorization for the targets you plan to test
- you need a standalone scanner rather than an AI-assisted skill bundle inside Claude Code
- you don't use Claude Code or an Anthropic-compatible agent runtime

## Facets
- artifact type: plugin
- maturity: active
- function: penetration-testing, security, mcp, prompt-engineering, developer-tools
- domain: security, penetration-testing, developer-tools
- platform: cli, cross-platform, windows
- tags: claude-code, claude-skills, bug-bounty, red-team, offensive-security, vulnerability-assessment, hackerone, burp-suite, skill-bundle, ethical-hacking, automation, macos, linux

## Member repositories
- elementalsouls/Claude-BugHunter (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:19.913734+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:52.711110+00:00, confidence not recorded.
  - readme: https://github.com/elementalsouls/Claude-BugHunter (fetched 2026-08-28T04:08:19.913734+00:00, sha 3b56d1d92e75)
  - homepage: https://elementalsouls.github.io/Claude-BugHunter (fetched 2026-08-29T09:21:44.903141+00:00, sha 80487a011b2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.