The Agent Skills Directory

[SAFE]: The skill provides a robust framework for creating interactive data observatory dashboards. It uses local Python scripts to process data and generate static HTML/JS artifacts without relying on external network dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied datasets from various formats (CSV, Excel, JSON).
Ingestion points: scripts/profile_data.py and scripts/build_treemap_dashboard.py read external files into the agent's context.
Boundary markers: The skill does not implement specific prompt delimiters for data content, instead relying on a structured profiling workflow to identify fields.
Capability inventory: The scripts are limited to reading input files and writing local JSON and HTML output. No network operations or arbitrary shell command execution capabilities are exposed.
Sanitization: The dashboard builder script includes basic XSS mitigation by escaping the '<' character when embedding raw data into the HTML template.
[DATA_EXPOSURE]: The skill demonstrates security awareness regarding sensitive data. The data profiling script defaults to excluding raw data samples from its output to prevent the accidental leakage of PII or sensitive business information into metadata files.

data-observatory-dashboard