The Agent Skills Directory

[SAFE]: The skill acts as a comprehensive reference for web security testing. All code snippets, payloads, and command-line examples are provided for educational purposes and manual security research.
[REMOTE_CODE_EXECUTION]: Documentation in reference/prototype-pollution-cheat-sheet.md includes strings representing reverse shell commands. These are clearly marked as research examples and are not executed by the skill.
[COMMAND_EXECUTION]: Several files provide example curl and python one-liners for checking security headers or testing for vulnerabilities. These are intended for manual execution by the security researcher.
[DATA_EXFILTRATION]: Payload examples throughout the reference files demonstrate how data can be exfiltrated via fetch() or XMLHttpRequest to educational domains (e.g., attacker.com). These are contextually appropriate for a pentesting reference skill.

client-side