data-science
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains guidelines for writing high-performance numeric code. No malicious instructions, obfuscation, or unauthorized data access patterns were found.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on processing external data files, creating a potential surface for indirect injection. It mitigates this risk by enforcing schema validation. Ingestion points: read_csv and read_parquet operations in rule files. Boundary markers: Recommended use of pandera schemas. Capability inventory: DataFrame mutation and aggregation. Sanitization: Explicit recommendation for Schema.validate at ingestion boundaries to prevent downstream errors.
Audit Metadata