Back to directory

claude-red

A curated library of offensive-security skill files that gives Claude expert methodology for authorized red-team engagements, from web exploitation to wireless and cloud attack paths.

claude-red

claude-red is a library of offensive-security skills for the Claude skills system, covering areas from SQL injection and EDR evasion to exploit development. Each skill is a structured file that primes Claude with the techniques, tooling, edge cases, and escalation paths for one attack surface, and skills load on demand based on the conversation rather than staying resident.

It is organized into categories such as web application, authentication and identity, Active Directory, wireless networks, cloud, mobile, and IoT and embedded devices, and it can be installed in full, cloned as a single category with a sparse checkout, or piped into a Claude Code system prompt. It is intended for authorized red-team engagements, bug-bounty triage, security research, CTF preparation, and operator training.

It is written in Python and released under the MIT license.

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.