The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources which represents a potential attack surface. However, it mitigates this risk by including explicit instructions in Rule 15 of SKILL.md for the agent to treat all file contents as inert data and to ignore any embedded instructions.
[EXTERNAL_DOWNLOADS]: All external sources cited in the skill's metadata and documentation refer to official repositories and technical documentation from trusted entities like Anthropic, Polars, and DuckDB, used solely for establishing analytical best practices.
[DYNAMIC_EXECUTION]: The skill provides guidance on the use of Python functions for data manipulation while emphasizing the need for purity and predictability, ensuring that dynamic execution remains within the intended analytical scope.

data-analysis