The Agent Skills Directory

[SAFE]: The skill provides educational content and best practices for database architecture. Analysis of all instructions and scripts reveals no evidence of malicious intent, prompt injection, or data exfiltration patterns.
[INDIRECT_PROMPT_INJECTION]: The skill includes a schema_validator.py script that processes external data by reading local project files (.prisma, .ts).
Ingestion points: Reads files matching **/prisma/schema.prisma and **/*.ts in the provided project path.
Boundary markers: None identified.
Capability inventory: The script is limited to read-only operations and console output; it contains no network, file-write, or dynamic execution capabilities.
Sanitization: Content is parsed for structural validation and output as text or JSON.
[COMMAND_EXECUTION]: The included Python script is a developer utility for local schema validation. It does not invoke external shell commands or perform any actions that could lead to privilege escalation or persistence.

database-design