AI Agent Skills

This repo offers notes and resources on ethical hacking, covering information gathering, scanning, web hacking, exploitation, and Windows/Linux hacking.

Create or refine promptfoo redteam setup configs: purpose, targets, plugins, strategies, frameworks, multi-input target inputs, policy text, grader guidance, contexts, a…

Run, rerun, inspect, and QA promptfoo redteam scans from generated redteam YAML or an existing redteam setup config. Use when executing `promptfoo redteam eval` or `prom…

Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.

End-to-end Android APK red-team pipeline — automated APK acquisition (Play Store + apkpure + apkmirror fallback), jadx decompilation, secret/URL/JWT/Firebase grep, pinne…

Skill-set loader for /hunt orchestrator. Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set. Use when /hunt has ju…

Write, refine, run, and QA non-redteam promptfoo eval suites after the target or provider already works: prompts, vars, test cases, assertions, model-graded rubrics, tra…