skills/openlark/skills/svgjs/Gen Agent Trust Hub

svgjs

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown documentation and reference files. No executable scripts, binaries, or configuration files that trigger side effects were detected.
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of the @svgdotjs/svg.js package from the standard npm registry. This is a well-known library for vector graphics manipulation.
  • [PROMPT_INJECTION]: The skill documents methods for importing raw SVG, HTML, and XML strings into the DOM, which represents a surface for indirect prompt injection if an agent is used to process untrusted data using these methods.
  • Ingestion points: references/utilities.md describes methods for importing data: draw.svg(), draw.html(), and draw.xml().
  • Boundary markers: The documentation does not provide instructions for using boundary markers or sanitization when importing external strings.
  • Capability inventory: The documentation describes capabilities for creating hyperlinks (SVG.A in references/containers.md), loading images (SVG.Image in references/text-image.md), and attaching event listeners (references/events.md).
  • Sanitization: No sanitization or escaping mechanisms are described for the data ingestion methods.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:17 AM
Security Audit — agent-trust-hub — svgjs