The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external database migration files which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Database migration files (Drizzle, Prisma, SQL, Alembic) referenced in the instructions in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the input files are provided.
Capability inventory: The skill suggests executing shell commands such as bunx drizzle-kit migrate, npx prisma migrate deploy, and bun test in SKILL.md.
Sanitization: There are no defined mechanisms for sanitizing or validating the contents of the migration files before they are processed or used in shell commands.

migration-guard