The Agent Skills Directory

[SAFE]: The skill is a functional documentation suite for the Polars library. Analysis of the instructions and provided examples shows no signs of malicious activity, obfuscation, or unauthorized data access. The provided examples for environment variable management and database connection strings use generic placeholders and represent standard industry practices for secure configuration.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process external data, which introduces a theoretical surface for indirect prompt injection.
Ingestion points: The skill documents numerous ingestion points including pl.read_csv, pl.scan_parquet, pl.read_json, pl.read_excel, and pl.read_database_uri across SKILL.md and references/io_guide.md.
Boundary markers: The instructions do not define specific delimiters or instructions to isolate the LLM from potential commands embedded within data values.
Capability inventory: The skill utilizes Bash(python:*) and Bash(uv:*) tools to execute Python code, granting the ability to read from and write to the filesystem and interact with network-based data sources.
Sanitization: No explicit sanitization or validation of data content for prompt injection is mentioned, which is consistent with the purpose of a general-purpose data processing library.

alterlab-polars