deck-swiss-international

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references Tailwind CSS via a well-known CDN (cdn.tailwindcss.com) and typography from Google Fonts (fonts.googleapis.com). These are standard resources for web design and represent legitimate functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted user content to populate HTML slide templates.
  • Ingestion points: User content is processed as described in the SKILL.md instructions to fill various slide layouts (S01-S22).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the user data.
  • Capability inventory: The skill generates static HTML and CSS based on the template.
  • Sanitization: There are no explicit instructions for escaping or sanitizing user-provided text before interpolation into the HTML structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:58 PM
Security Audit — agent-trust-hub — deck-swiss-international