deck-guizang-editorial

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided markdown content and interpolate it into a predefined HTML presentation structure.
  • Ingestion points: User-supplied content from the primary prompt and data files (like example.md) are used to populate the slide layouts.
  • Boundary markers: There are no explicit delimiters or instructions defined in SKILL.md to distinguish user data from the generation logic.
  • Capability inventory: The skill produces a single-file HTML document intended for web rendering, which can include CSS and potentially JavaScript.
  • Sanitization: The instructions do not specify any validation or sanitization procedures for the external content before it is rendered.
  • [EXTERNAL_DOWNLOADS]: The template uses external resources for styling and typography from well-known services.
  • Evidence: The example.html file fetches the Tailwind CSS framework from cdn.tailwindcss.com and typography assets from fonts.googleapis.com.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:00 AM