The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an external PostgreSQL database, specifically schema metadata, index definitions, and performance statistics. This creates a surface where malicious database content (such as specifically crafted table names or query logs) could theoretically influence the agent's reasoning.
Ingestion points: Results from SQL queries targeting pg_stat_user_tables, pg_tables, pg_indexes, pg_stat_statements, and pg_constraint as defined in SKILL.md.
Boundary markers: None present to delimit database-sourced data from the skill's instructions.
Capability inventory: The skill utilizes read-only SELECT queries to retrieve table metadata and execution statistics.
Sanitization: The skill does not implement specific filtering or sanitization for the metadata retrieved from the database system catalogs.

find-hypertable-candidates