skills/vite-hub/drop/data-explorer/Gen Agent Trust Hub

data-explorer

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's HTML template and build script reference external resources, including the Vega and Vega-Lite visualization libraries from the jsDelivr CDN and dashboard assets (CSS/JS) from the vendor's domain (drop.vitehub.dev). These are standard practices for web-based visualization tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data sources such as CSV and JSON files. To mitigate risks like XSS when rendering this data in the dashboard, the client-side rendering logic (app.js) implements an escape function that sanitizes HTML entities (&, <, >, ") before applying any markdown-like formatting.
  • [DYNAMIC_EXECUTION]: The build process involves the agent writing and executing a data preparation script (prep.py or prep.mjs) to aggregate raw data. Additionally, the build.mjs script dynamically imports the playwright library to generate screenshots of the dashboard. These actions are within the expected functional scope of a data analysis tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 04:36 PM