The Agent Skills Directory

[SAFE]: The skill consists primarily of markdown documentation and a Python utility script intended for local schema validation. The script analyzes file naming conventions and schema structure without executing external code or performing network operations.
[PROMPT_INJECTION]: The skill identifies and processes external schema files (.prisma, .ts), which presents a surface for indirect prompt injection if those files contain malicious instructions disguised as comments or data.
Ingestion points: The schema_validator.py script and the agent's file tools read content from the local project path.
Boundary markers: No explicit XML delimiters or specific boundary instructions are used when interpolating file content into the agent's context.
Capability inventory: The skill includes Read, Write, Edit, Glob, and Grep tools, which allow the agent to modify the project based on its findings.
Sanitization: There is no specific sanitization of the contents read from schema files to prevent instructions from influencing agent behavior.

database-design