The Agent Skills Directory

[SAFE]: The skill instructions proactively address security risks by mandating that API keys be stored in environment variables rather than configuration files.
[COMMAND_EXECUTION]: The skill includes a local utility script scripts/check-output.py. Analysis of the source code confirms it is used solely for validating the structure and content of generated deliverables. It uses standard library modules (re, sys, pathlib) to perform string matching and regex checks. It does not perform network requests, file writes, or utilize unsafe execution functions like eval() or exec().
[DATA_EXFILTRATION]: No data exfiltration patterns or unexpected network operations were detected. The skill's design focuses on 'read-only' lookups for initial stages and requires explicit user approval for any 'write' or 'enroll' actions.

leadmagic-mcp