skills/ssdeanx/agentstack/ai-elements/Gen Agent Trust Hub

ai-elements

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill provides components like JSXPreview and Artifact that ingest and render AI-generated content.\n
  • Ingestion points: The jsx prop in JSXPreview (references/jsx-preview.md) and the code prop in CodeBlock (references/code-block.md).\n
  • Boundary markers: Not explicitly present in the demo code, though the skill is intended for UI display.\n
  • Capability inventory: The components focus on UI rendering (e.g., Markdown, syntax highlighting, icons).\n
  • Sanitization: JSXPreview utilizes react-jsx-parser which is more secure than raw HTML rendering.\n- [Dynamic Execution] (SAFE): Documentation for the StackTrace component includes a backend example that uses eval() to generate errors for demonstration. This code is not part of the skill's execution logic.\n- [External Downloads] (SAFE): The skill references assets from trusted domains such as vercel-storage.com and unsplash.com. The ai-elements package itself is a standard development library.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:26 PM