The Agent Skills Directory

[SAFE]: The skill serves its primary purpose as a development utility for skill scaffolding and packaging without any hidden or malicious functionality.
[DYNAMIC_EXECUTION]: The included Python scripts (init_skill.py, package_skill.py, quick_validate.py) perform deterministic file system operations like directory creation and zipping. No evidence of eval(), exec(), or runtime compilation of untrusted code was found.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-generated skill content, it implements safe parsing practices. Specifically, quick_validate.py utilizes yaml.safe_load() to handle YAML frontmatter, which prevents the execution of arbitrary Python objects during deserialization.
[DATA_EXFILTRATION]: No network operations (e.g., curl, requests) or access to sensitive local file paths (e.g., .env, .ssh, .aws) were detected in any of the scripts or instructions.
[PROMPT_INJECTION]: The SKILL.md content provides legitimate technical guidance and process steps. It does not contain instructions aimed at bypassing AI safety filters or overriding system prompts.

skill-creator