data-report

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied data (CSV, Excel, JSON) to generate visual reports, which creates a potential surface for indirect prompt injection if the data contains malicious instructions.
  • Ingestion points: Data files in CSV, Excel, or JSON format.
  • Boundary markers: No explicit markers are defined to isolate data from generated instructions.
  • Capability inventory: The skill generates HTML and JavaScript to render charts.
  • Sanitization: No explicit sanitization or escaping logic is described for the dynamic content.
  • [EXTERNAL_DOWNLOADS]: The example template references well-known external CDNs for resources.
  • Fetches visualization libraries from jsDelivr.
  • Loads CSS framework from Tailwind CDN.
  • Retrieves typography from Google Fonts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:56 PM
Security Audit — agent-trust-hub — data-report