polars

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the polars Python library (version 1.41.2). This is a well-established, reputable open-source library used for data manipulation and analysis.
  • [COMMAND_EXECUTION]: The documentation includes shell commands for environment setup and package installation using the uv tool, which is a common and legitimate practice in Python development.
  • [PROMPT_INJECTION]: The skill enables an attack surface for indirect prompt injection by providing tools to ingest data from external sources (CSV, Parquet, JSON, and databases).
  • Ingestion points: Data reading functions such as pl.read_csv, pl.scan_parquet, and pl.read_database documented in references/io_guide.md allow the agent to load content from external files and network locations.
  • Boundary markers: The provided code examples do not explicitly demonstrate the use of delimiters or 'ignore' instructions to isolate processed data from the agent's control logic.
  • Capability inventory: The skill allows the agent to perform extensive data transformations and analytical queries using the native Polars expression API.
  • Sanitization: The skill does not specifically address data sanitization for injection risks, relying instead on the strict schema enforcement and type system of the underlying library.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 02:13 AM