d3js-data-visualization

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official D3.js library for installation via npm and provides a CDN link to d3js.org.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data for rendering.
  • Ingestion points: Data enters the visualization logic through the drawChart(data) and setupResponsiveChart(containerId, data) functions in SKILL.md.
  • Boundary markers: There are no explicit markers or instructions to the agent to treat the input data as purely passive or to ignore embedded control instructions.
  • Capability inventory: The skill uses D3 to manipulate the DOM, generate SVG content, and implement interactive tooltips using the .html() method.
  • Sanitization: While the documentation suggests filtering for numeric validity (nulls/NaN), it lacks guidance on sanitizing or escaping string properties before rendering them as HTML in tooltips, creating a potential XSS vector.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:36 AM