claude-d3js-skill

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Risk. 1. Ingestion points: Untrusted data enters the agent context via the data property in the chart components located in assets/chart-template.jsx and assets/interactive-template.jsx. 2. Boundary markers: There are no delimiters or instructions to ignore embedded commands within the processed data. 3. Capability inventory: The skill uses d3.select().html() to dynamically generate tooltip content in SKILL.md and assets/interactive-template.jsx, which allows for direct DOM manipulation. 4. Sanitization: No sanitization or HTML escaping is performed on data properties like d.label before they are interpolated into the tooltip HTML.
  • [EXTERNAL_DOWNLOADS]: Fetches the D3.js library from its official repository via CDN at https://d3js.org/d3.v7.min.js. This is a well-known and authoritative source for the library.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:37 AM