The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides logic for reading and transforming database records, which presents an ingestion surface for untrusted data.\n
Ingestion points: Data is fetched via database queries (e.g., SELECT id, address_string FROM users in SKILL.md).\n
Boundary markers: No explicit instructions to the agent to ignore instructions embedded within the database data are present.\n
Capability inventory: The skill utilizes shell scripts (scripts/test-migration.sh), Python scripts (assets/data-migration-script.py), and direct database query execution capabilities.\n
Sanitization: While code snippets use parameterized queries for SQL safety, there is no verification or sanitization of the data content for potential prompt injection attacks.\n- [COMMAND_EXECUTION]: The skill involves the execution of migration-related shell scripts and standard ORM command-line interfaces.\n
Evidence: References scripts/test-migration.sh and provides examples using npx sequelize-cli, npm run typeorm, and npx prisma.

database-migration