The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local database schema files, which could theoretically contain untrusted instructions embedded in comments or metadata.
Ingestion points: Reads content from prisma/schema.prisma, src/db/schema.ts, and *.entity.ts files using cat and find commands.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill can execute file system commands (ls, grep, cat, find) and utilize npx to run database management tools.
Sanitization: No sanitization or validation of the schema file content is performed before the agent processes it.
[COMMAND_EXECUTION]: The skill utilizes standard shell commands to discover and read database configurations.
Employs ls, grep, cat, and find to navigate the file system and inspect schema definitions.
Instructs the agent to run official ORM CLI tools such as prisma, drizzle-kit, and typeorm to manage migrations and generate code.
[EXTERNAL_DOWNLOADS]: The skill relies on external tools and packages that may be fetched at runtime.
Uses npx to execute commands for Prisma, Drizzle, and TypeORM, which are well-known services for database management.

managing-database-schemas