The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides utility scripts (scripts/init_skill.py and scripts/package_skill.py) intended to be executed by the agent to automate the creation of skill directory structures and the packaging of skills into zip files. These scripts utilize standard Python libraries for local file and directory management.
[DYNAMIC_EXECUTION]: The initialization script (scripts/init_skill.py) generates template files, including an executable Python script (scripts/example.py), from internal templates. This is a low-risk behavior consistent with the skill's primary purpose as a project generator.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions to generate instructions for new skills, creating a potential surface for indirect prompt injection. Evidence: 1. Ingestion points: User requests for skill functionality and behavior. 2. Boundary markers: No explicit delimiters are mandated in the generated SKILL.md templates. 3. Capability inventory: Local file writing and execution via the provided Python scripts. 4. Sanitization: The quick_validate.py script performs basic sanitization by checking for angle brackets and enforcing naming conventions.

skill-creator