polars
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for the agent to ingest and process data from external files (CSV, JSON, Excel, Parquet), SQL databases, and cloud storage providers (S3, GCS, Azure). This establishes an attack surface for indirect prompt injection if untrusted data containing malicious instructions is processed by the agent.
- Ingestion points: Multiple methods for reading data are documented, including
pl.read_csv,pl.read_parquet,pl.read_json,pl.read_excel, andpl.read_databaseinSKILL.mdandreferences/io_guide.md. - Boundary markers: The documentation does not provide specific instructions or markers to delimit external data from agent instructions.
- Capability inventory: The library includes capabilities for file system access and network operations (via database connectors and cloud SDKs).
- Sanitization: No explicit sanitization or validation routines for external content are included in the provided reference materials.
Audit Metadata