The Agent Skills Directory

[SAFE]: The instructional content in SKILL.md and its references is designed to guide developers in building skills. It does not contain any prompt injection attempts or instructions to bypass safety filters.
[COMMAND_EXECUTION]: The skill includes Python scripts (init_skill.py, package_skill.py) that facilitate local development tasks such as directory creation, file writing, and packaging archives. These operations are essential to the skill's utility and are implemented using standard library functions without exposing the system to command injection or unauthorized access.
[SAFE]: The validation script (quick_validate.py) utilizes yaml.safe_load() to parse skill metadata. This is a secure implementation that mitigates risks associated with arbitrary code execution during the deserialization of YAML data.
[SAFE]: No network operations, external downloads, or exfiltration patterns were identified. All script actions are confined to the local filesystem as part of the skill development workflow.

skill-creator