The Agent Skills Directory

[SAFE]: The skill serves as a documentation framework for modular design and does not contain executable code or malicious instructions.
[COMMAND_EXECUTION]: The documentation references local Python scripts (skill_analyzer.py, tokens.py, abstract_validator.py) and basic shell utilities (find, wc, awk, chmod) for analyzing skill complexity and validating directory structures. These are presented as standard development tools.
[INDIRECT_PROMPT_INJECTION]: The skill describes tools that process other skill files, creating an ingestion point (analysis of SKILL.md and module files). While boundary markers and specific sanitization methods for these tools are not detailed in the instructions, the capability inventory is limited to local analysis and reporting scripts, posing minimal risk in this context.

modular-skills