Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Claude-BugHunter

Claude-BugHunter: A self-contained Claude skill bundle for bug hunting and external red-team work.

What problem it solves

Generic security prompts and fragmented report collections do not scale across repeated bug-hunting engagements. The project addresses this with structured methodology, vulnerability-specific skills, enterprise attack matrices, validation gates, reporting guidance, and engagement coordination for authorized external testing.

Key features

  • Topic-triggered security skills — Skills load automatically when a user describes what they are testing, allowing natural-language use without invoking each skill by name.

    Source: README, skills

  • Disclosed-report hunting patterns — The web application layer provides per-class detection patterns, payloads, bypass tables, and chain templates derived from disclosed HackerOne reports.

    Source: README

  • Enterprise perimeter coverage — Enterprise-focused skills cover identity and infrastructure platforms, including M365 and Entra ID, Okta, vCenter, SSL-VPN appliances, SharePoint, and cloud IAM.

    Source: README

  • Structured engagement workflow — A non-linear workflow guides reconnaissance, attack-surface ranking, hunting, validation, and reporting, with a validation gate before submission.

    Source: README, engine, USAGE.md

  • Multi-harness installation — The skills use the Agent Skills format and can be installed across several agent harnesses, with optional Burp MCP integration.

    Source: README, scripts

Quick start

Copied verbatim from the project's README.

/plugin marketplace add elementalsouls/Claude-BugHunter
/plugin install claude-bughunter@elementalsouls
# macOS / Linux
bash scripts/install.sh

# Windows (PowerShell)
pwsh ./scripts/install.ps1
> Testing acme.com — an in-scope HackerOne target. Run recon and rank the surface.

  ⟳ loading skills: web2-recon, offensive-osint, bb-methodology …
    → subdomain enum (subfinder + crt.sh) … 47 hosts
    → live hosts (httpx) … 12 · tech fingerprint … 6 distinct stacks
    → ranked surface: api.acme.com (GraphQL, introspection ON)  ← start here
                      auth.acme.com (OAuth, SSO)               ← hunt-oauth

  Next: want me to probe the GraphQL introspection + OAuth redirect_uri?

Who it may suit

Inference: may suit bug-bounty hunters, web application pentesters, and external red-team operators working on owned or explicitly authorized assets.

Topics to discuss

  • Which disclosed-report patterns should be added or refreshed next?

  • How can the 7-Question Gate be improved for different bug-bounty programs?

  • Which external enterprise platforms need dedicated hunting or attack-chain skills?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/elementalsouls/Claude-BugHunter#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/elementalsouls/Claude-BugHunter

Comments

…