data-visualization

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional guidelines for data visualization best practices. It does not contain any executable code, command injections, or instructions to access sensitive data.
  • [EXTERNAL_DOWNLOADS]: The skill recommends using standard, well-known libraries such as Chart.js (via CDN), Plotly, Matplotlib, and Seaborn for rendering charts. These are recognized industry-standard tools and are cited for their legitimate purpose of visualization.
  • [SAFE]: The skill processes external data for visualization, which presents a surface for indirect prompt injection. 1. Ingestion points: files matching '/data' or '/visualization' (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Generates HTML/JS, Python code, and Mermaid diagrams. 4. Sanitization: Absent. No dangerous capabilities are exposed through this surface.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 04:15 PM
Security Audit — agent-trust-hub — data-visualization