The Agent Skills Directory

[SAFE]: The skill does not contain any executable scripts, binary files, or external network requests. It is entirely composed of natural language instructions and technical guidelines for database architecture.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user inputs (database requirements and domain descriptions) to generate architectural designs and migration code.
Ingestion points: User-provided business requirements and access patterns processed in the Response Approach section.
Boundary markers: Absent; the skill does not define specific delimiters for user-provided data.
Capability inventory: The skill is limited to generating text-based recommendations, schema designs, and code snippets (ORM, SQL). It lacks capabilities for autonomous file system modification, shell execution, or network operations.
Sanitization: Not present, but the risk is negligible as the output is intended for human review and the skill lacks exploitable tool access.

database-architect