The Agent Skills Directory

[PROMPT_INJECTION]: The DEEPENING.md workflow involves processing untrusted data from external project sources, which constitutes an indirect prompt injection surface.
Ingestion points: The agent is directed to scan PR titles, descriptions, and comments, as well as issue trackers.
Boundary markers: No specific delimiters or safety instructions are provided to ensure the agent ignores instructions embedded in the analyzed PR content.
Capability inventory: The agent possesses the capability to perform deep codebase analysis and propose architectural refactors based on the processed information.
Sanitization: The instructions do not define any sanitization or validation logic for external metadata or comments prior to analysis.

codebase-design