The Agent Skills Directory

[SAFE]: The package_skill.py script implements robust security checks to prevent directory traversal by validating that all files included in a package are contained within the intended root directory.
[SAFE]: The skill's packaging logic explicitly identifies and excludes symbolic links, mitigating the risk of unauthorized file inclusion or access to sensitive data outside the skill folder.
[SAFE]: The init_skill.py script performs input sanitization on user-provided skill names using regular expressions ([a-z0-9-]+), ensuring that directory names and filenames are restricted to safe characters.
[DYNAMIC_EXECUTION]: The quick_validate.py script uses yaml.safe_load() for metadata parsing, which is a secure implementation that prevents the execution of arbitrary code during the deserialization of YAML data.
[COMMAND_EXECUTION]: The skill includes Python scripts designed to perform legitimate filesystem operations, such as creating directories, writing template files, and generating ZIP archives, which are necessary for its function as a development tool.

skill-creator