The Agent Skills Directory

[SAFE]: No security issues were detected. The skill primarily consists of documentation and usage examples for an external data API belonging to the skill author.
[COMMAND_EXECUTION]: The documentation includes curl commands as examples for interacting with the API. These are standard, expected patterns for an API-focused skill.
[DYNAMIC_EXECUTION]: In references/common-patterns.md, the skill provides a static Python template for performing local statistical calculations on data. This is a benign utility for the skill's primary purpose of data analysis.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates fetching data from external API endpoints (api.tryopendata.ai). While the data returned could theoretically contain instructions intended to influence the agent (indirect prompt injection), this is an inherent risk of data-fetching tools. The skill documentation describes a remote SQL sandbox with strict allowlists (SELECT only) and resource limits, which mitigates risks associated with processing these results.

opendata-api