Back to directory

claude-osint

A library of Claude skill files that turn Claude into an external reconnaissance operator for authorized red-team and bug-bounty engagements.

claude-osint

claude-osint is a library of skills for the Claude skills system that gives Claude expert-level methodology for external reconnaissance during authorized red-team and bug-bounty engagements. A core pair of skills covers strategic and procedural methodology, such as asset-graph discipline and severity scoring, alongside a tactical arsenal of probe paths, regular expressions, and scoring rules.

Six additional organization-scale skills add enterprise attack-surface reasoning: mapping a legal entity to its owned infrastructure, scoring email and domain spoofability, quantifying exposure risk in a financial model with a board-ready summary, running a continuous re-scan and monitoring loop, assessing cloud storage and SaaS exposure, and mapping identity-provider tenants and federation. Each skill is a self-contained directory with its own documentation, and the project reports passing a 56-prompt self-evaluation with no fabricated findings.

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.