managing-data-catalogs
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides configuration patterns and architectural guides for data catalogs using well-known services and industry-standard libraries. No malicious code, obfuscation, or unauthorized access patterns were identified.- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external catalogs and cloud storage, which represents an indirect prompt injection surface (Category 8).
- Ingestion points: Multiple files including
duckdb-catalog.md,rest-catalog.md, andhive-metastore.mddescribe fetching and processing table data. - Boundary markers: Not explicitly present in the documentation snippets.
- Capability inventory: The skill enables SQL execution via DuckDB and Python-based data processing via Pandas and PyIceberg.
- Sanitization: As these are connectivity and setup examples, input validation and data sanitization are not explicitly addressed.
Audit Metadata