The Agent Skills Directory

[SAFE]: The skill instructions and associated reference files do not contain any malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution.\n- [COMMAND_EXECUTION]: Shell commands found in the files (e.g., npm install express, brew services start mongodb-community) are provided exclusively as examples or templates for the user within the generated documentation. They are not intended for execution by the AI agent in its own environment.\n- [DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file access, or unauthorized network activity was found. The skill operates solely on provided text and internal reference files.\n- [PROMPT_INJECTION]: The skill uses clear, instructional language and structured workflows with validation layers. No bypass markers or adversarial role-play instructions were detected.

create-documentation