architecture-viz-studio

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill incorporates standard web development libraries, including Three.js, GSAP, and post-processing effects, which are referenced from the jsDelivr CDN and Google's static servers (for Draco decoders). These are well-known and trusted sources for industry-standard development assets.
  • [PROMPT_INJECTION]: The skill implements a collaborative 'Edit Mode' that captures user feedback and instructions. This data is handled locally via a bridge script and subsequently read by the agent to perform project revisions. This ingestion surface is a documented part of the skill's primary function and does not exhibit patterns of malicious intent or behavior bypass.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 08:04 AM
Security Audit — agent-trust-hub — architecture-viz-studio