build-dashboard

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches legitimate, standard charting libraries (Chart.js and its date adapter) from the jsDelivr CDN. These are well-known, industry-standard resources used to provide the dashboard's core functionality.
  • [DATA_EXPOSURE]: The skill is designed to embed data (either queried from a connected warehouse or provided by the user) into a generated HTML file. While this handles data, it does so explicitly to fulfill the user's request to create a dashboard. No evidence was found of data being sent to unauthorized third-party servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (CSV, query results) and interpolates it into an HTML template. While this is an ingestion surface, the risk is mitigated as the output is a static HTML file intended for the user's browser, and the instructions focus on structured data handling rather than executing instructions embedded within that data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:21 PM
Security Audit — agent-trust-hub — build-dashboard