The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for advanced PostgreSQL features. All provided SQL snippets (CTEs, recursive queries, window functions, etc.) are standard, well-documented patterns consistent with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill includes SQL utility queries for monitoring database health, such as inspecting pg_stat_activity to view active queries and pg_total_relation_size for table sizes. These are standard database administration tasks and do not represent a security risk when executed in an authorized environment.
[DATA_EXFILTRATION]: No network-related commands (e.g., curl, wget) or external data transmission patterns were identified. The skill operates entirely within the scope of database query generation and analysis.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or connection strings were found. The skill uses generic table and column names in its examples.
[PROMPT_INJECTION]: The instructions and workflow descriptions follow standard AI agent skill patterns and do not contain attempts to override safety filters or bypass system instructions.

postgresql-advanced-sql