The Agent Skills Directory

[COMMAND_EXECUTION]: The included Python scripts (init_skill.py, package_skill.py) perform local file system operations including directory creation, file writing, and setting executable permissions (chmod 755), which are necessary for the skill's function of project initialization.
[EXTERNAL_DOWNLOADS]: The skill requires the PyYAML library for its validation script to parse metadata in skill files.
[PROMPT_INJECTION]: The skill provides an indirect prompt injection surface by ingesting user-provided descriptions and examples to generate skill files. Mandatory Evidence Chain: (1) Ingestion points: User input provided during the skill creation process (SKILL.md). (2) Boundary markers: Absent. (3) Capability inventory: Local file writing via scripts/init_skill.py. (4) Sanitization: No explicit sanitization or input validation logic is present in the skill instructions.

skill-creator