The Agent Skills Directory

[SAFE]: The skill performs standard file system operations to audit project content. It operates within a well-defined scope, reading from design directories and scanning asset/source folders to produce documentation in a dedicated docs folder.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading game design documents (GDD) from design/gdd/*.md.
Ingestion points: Reads project-specific design files and system indexes (SKILL.md).
Boundary markers: The instructions do not specify delimiters or 'ignore' instructions for the parsed content.
Capability inventory: The skill uses Read, Glob, Grep, and Write tools to analyze files and save a markdown report.
Sanitization: There is no explicit sanitization of the content extracted from the design documents before it is summarized in the final report. However, since the skill has no network access or command execution capabilities, the impact of a potential injection is restricted to poisoning the generated audit report.

content-audit