The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Grep and Glob tools to search through local files.
It searches for content patterns (e.g., 'N enemies', '## Summary') in the design/gdd/ directory.
It scans for specific file extensions (e.g., .unity, .json, .prefab, .asset) in the Assets/ directory to count implemented items.
[INDIRECT_PROMPT_INJECTION]: The skill reads and processes external content from Game Design Documents (GDDs) in the design/gdd/ folder.
Ingestion points: Reads text from markdown files in the design/gdd/ directory.
Boundary markers: None explicitly defined for the ingested text.
Capability inventory: The skill has Read, Write, Grep, and Glob capabilities. It does not have network access or arbitrary code execution capabilities.
Sanitization: The skill extracts lists and counts from the text for report generation rather than executing instructions from the data.
[SAFE]: The skill operates entirely within the local repository context, specifically targeting the Assets/, design/, and docs/ directories. It does not perform network operations, access sensitive credentials, or attempt to escalate privileges.

content-audit