The Agent Skills Directory

[SAFE]: The skill is focused on documentation and requirements gathering. It operates entirely within the repository, reading existing files to establish context and writing new documentation files. No unauthorized network access, credential exposure, or command execution patterns were found.
[INDIRECT_PROMPT_INJECTION]: The skill defines a clear ingestion surface for external data by reading repository files and 'context-brief' artifacts. It incorporates robust defensive measures by requiring specific metadata (artifact: context-brief, status: validated) and performing SHA-256 hash comparisons to ensure input integrity and prevent the use of stale or modified data. Its capabilities are limited to local file read/write operations within the docs/ directory.
[PROMPT_INJECTION]: No patterns of behavior override or safety bypass were detected. The instructions enforce strict adherence to Simplified Technical English (STE) and a predefined PRD template.

requirements