polars

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a documentation resource for Polars, a legitimate and well-known high-performance data processing library.
  • [EXTERNAL_DOWNLOADS]: The documentation includes instructions for installing the 'polars' package using standard package managers, which is a required step for using the library.
  • [COMMAND_EXECUTION]: The skill demonstrates standard library functions for reading and writing local files in multiple formats (CSV, Parquet, JSON), which is the intended purpose of the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes capabilities to ingest external data, defining a potential surface for indirect prompt injection. 1. Ingestion points: read_csv, scan_csv, read_parquet, and read_json operations described in SKILL.md. 2. Boundary markers: None mentioned. 3. Capability inventory: File system write operations via write_csv, write_parquet, and write_json. 4. Sanitization: Not described in the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 05:15 AM
Security Audit — agent-trust-hub — polars