skills/jackspace/claudeskillz/polars/Gen Agent Trust Hub

polars

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill documentation includes instructions to install the polars library via pip. As Polars is a standard and well-known package in the data science ecosystem, this is a low-risk download per the [TRUST-SCOPE-RULE].\n- PROMPT_INJECTION (MEDIUM): The skill establishes a surface for indirect prompt injection due to its core function of processing untrusted external data combined with file-writing capabilities.\n
  • Ingestion points: Data is ingested from external files using pl.read_csv(), pl.scan_csv(), pl.read_parquet(), and pl.read_json() as documented in SKILL.md.\n
  • Boundary markers: No instructions or delimiters are provided in the code snippets to separate data from potentially malicious instructions embedded within the files.\n
  • Capability inventory: The skill possesses the capability to write processed data back to the filesystem using write_csv, write_parquet, and write_json, which serves as an external output channel.\n
  • Sanitization: No evidence of data sanitization, schema validation, or filtering is shown for the ingested content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:25 AM