Back to directory

claude-bughunter

A Claude Code skill bundle for authorized bug-bounty and red-team work, with skills, slash commands and curated attack patterns drawn from disclosed vulnerability reports, plus enterprise platform attack matrices.

Visit website (opens in a new tab)elementalsouls.github.io
claude-bughunter

claude-bughunter is a skill bundle for the Claude Code skills system that adds bug-hunting and red-team capabilities: web-application detection patterns and chain templates drawn from disclosed HackerOne reports across 24 vulnerability classes, enterprise platform attack chains for systems such as Microsoft 365/Entra, Okta, vCenter, SSL-VPN appliances, SharePoint and cloud IAM, and a reporting workflow covering finding validation, severity rating, out-of-scope rebuttals and PII redaction.

Skills load automatically based on the topic being tested, described in plain English, without needing to be invoked by name. It installs either as a Claude Code plugin, which keeps the skills namespaced and updatable, or by cloning the repository and running an install script that copies the skills and commands into the user's configuration directory. The project states it is intended for authorized engagements and public training platforms.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.