The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns detected across all 10 threat categories.
[DATA_EXPOSURE] (SAFE): The scripts interact only with the provided skill directory and the user-specified output directory. Path resolution is handled via pathlib.Path.resolve(), and no sensitive system paths or credentials are accessed.
[COMMAND_EXECUTION] (SAFE): There are no instances of os.system, subprocess, eval, or exec. The code performs purely logic-based validation and standard file compression.
[EXTERNAL_DOWNLOADS] (SAFE): No network operations or external dependency installations are performed. The scripts rely entirely on Python's standard library (sys, zipfile, pathlib, re, os).
[METADATA_POISONING] (SAFE): The quick_validate.py script includes active sanitization for metadata, enforcing hyphen-case naming conventions and explicitly forbidding angle brackets in descriptions to prevent basic injection or formatting bypasses.

skill-creator