d3-viz
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for ingesting and rendering external datasets, which constitutes an attack surface for indirect injection.
- Ingestion points: The drawVisualization and chart-specific functions (e.g., drawBarChart, drawHeatmap) in SKILL.md and references/d3-patterns.md ingest data arrays provided at runtime.
- Boundary markers: The templates do not include explicit delimiters or instructions to treat data as untrusted content.
- Capability inventory: The skill generates code that creates DOM elements. The interactive tooltip example specifically uses the .html() method to render data-driven labels (d.label), which could facilitate Cross-Site Scripting (XSS) if the ingested data source is controlled by an attacker.
- Sanitization: No explicit escaping or sanitization logic is provided in the documentation templates to protect against malicious data content.
- [EXTERNAL_DOWNLOADS]: The skill references the official D3.js CDN (https://d3js.org/d3.v7.min.js) in SKILL.md. This is a well-known and reputable source for the D3 library.
Audit Metadata