data-visualizer

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data to generate visualization code in HTML, React, and Mermaid formats, which creates a potential surface for instructions embedded in data to influence the visualization logic.
  • Ingestion points: Input data provided for chart and dashboard generation in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore instructions" markers for input data are explicitly defined in the skill files.
  • Capability inventory: Generates HTML/React files and invokes other ecosystem skills (moai-officer, moai-writer) for file conversion and review.
  • Sanitization: No explicit data sanitization or escaping mechanisms for the input data are described in the instructions.
  • [EXTERNAL_DOWNLOADS]: Fetches the Chart.js library from a well-known public content delivery network.
  • Evidence: The skill uses "https://cdn.jsdelivr.net/npm/chart.js" to render charts, as specified in references/data-visualizer/guide.md.
  • [DYNAMIC_EXECUTION]: Generates executable dashboard code (HTML/React) at runtime based on user data and selected visualization strategies.
  • Evidence: The skill assembles index.html and React components using libraries like Recharts, Chart.js, and Tremor as described in the Outputs section of SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — data-visualizer