The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external database schemas and migration specifications through its core scripts, which can influence the agent's output and recommendations.\n
Ingestion points: The scripts migration_planner.py and compatibility_checker.py ingest JSON data from files like sample_database_migration.json and schema definitions.\n
Boundary markers: The skill does not define explicit delimiters or instructions to treat data from these ingestion points as untrusted, which could allow instructions embedded in schemas to affect the agent's behavior.\n
Capability inventory: The tools are restricted to local file reading and writing. They do not possess autonomous network access or the ability to execute arbitrary shell commands.\n
Sanitization: The scripts parse the input files as structured JSON but do not perform sanitization or filtering on the text content of the fields to prevent natural language instruction injection.

migration-architect