The Agent Skills Directory

[Command Execution] (LOW): The skill invokes local Python scripts (convert_skills.py, remove_duplicates.py, final_cleanup.py) to perform automated file modifications. These operations are consistent with the skill's stated purpose of project maintenance.
[Prompt Injection] (LOW): Identifies an Indirect Prompt Injection surface (Category 8) as the skill is designed to ingest and process untrusted markdown files.
Ingestion points: Processes existing and new SKILL.md files within the .agent-skills directory.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the contents of the processed files as untrusted data.
Capability inventory: The skill utilizes python3 execution, along with Read, Write, and Edit tools to modify the file system.
Sanitization: While the skill describes regex-based heading conversion, it does not explicitly define sanitization protocols for the data being processed.

skill-standardization