polars
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from various sources including CSV, Parquet, JSON, databases, and cloud storage.
- Ingestion points: The skill documents numerous data ingestion methods such as
pl.read_csv,pl.scan_parquet, andpl.read_databasewithinreferences/io_guide.mdandSKILL.md. - Boundary markers: The instructions do not define specific delimiters or provide guidance to the agent on identifying or ignoring instructions that may be embedded within the data content itself.
- Capability inventory: The library enables significant capabilities that could be targeted by an injection attack, including file system writes (
write_csv,write_parquet), database writes (write_database), and interaction with cloud infrastructure (AWS S3, Azure Blob, GCS). - Sanitization: No specific sanitization or filtering logic is prescribed for data content processed by the agent using this skill.
Audit Metadata