designing-data-storage
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a comprehensive educational resource for data storage formats and lakehouse architectures.
- [SAFE]: External dependencies referenced in installation guides, such as PyArrow, Delta Lake, and Apache Hudi, are industry-standard libraries or originate from trusted open-source organizations.
- [INDIRECT_PROMPT_INJECTION]: The skill illustrates methods for an agent to ingest data from external sources such as Parquet files and cloud storage buckets. This creates a theoretical surface for indirect prompt injection if the ingested data contains malicious instructions.
- Ingestion points: Data loading functions in
SKILL.md(e.g.,pl.read_parquet,DeltaTable.to_pandas) andreferences/iceberg.md(e.g.,table.scan().to_pandas()). - Boundary markers: None used in the provided code examples.
- Capability inventory: The skill provides patterns for reading, searching, and writing data across multiple storage backends.
- Sanitization: No sanitization logic is included in the provided code templates.
Audit Metadata