Browse all 9 articles in this open-source series. An authorization-first series on routing repeatable security research workflows for AI agents.
Featured starting point
A source-backed guide to reverse-skill's AI skill router, tool-index workflow, evidence model, and authorization boundaries.
Suggested learning path
01 → 09
A source-backed guide to reverse-skill's AI skill router, tool-index workflow, evidence model, and authorization boundaries.
A scope-first walkthrough of reverse-skill's routing rules, tool index, case initialization, evidence timeline, and report handoff.
Deploy reverse-skill safely across Windows, Ubuntu, Kali, and compatible AI clients with pinned tools, isolated cases, and regression gates.
Analyze the client-neutral reverse-skill architecture from structured routing rules through authorization gates, scenario skills, tool adapters, and report evidence.
A fixture-driven method for reading reverse-skill scripts, routing configuration, case initialization, tool indexes, and evidence/report generators.
A reproducible benchmark plan for reverse-skill route latency, tool discovery, case initialization, artifact processing, report generation, and analyst time.
An authorization-first operations guide for reverse-skill scopes, network profiles, secrets, untrusted samples, tool permissions, evidence retention, and incident response.
Compare reverse-skill with ad-hoc commands, single-domain playbooks, commercial platforms, and custom orchestration by authorization, coverage, evidence, portability, and operations.
A practical capstone for versioned routing rules, authorization receipts, tool capability manifests, evidence graphs, regression fixtures, and accessible reports.
