guizang-ppt-skill

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The generated presentations fetch assets from reputable content delivery networks. These include Google Fonts for typography, Lucide icons from unpkg, MapLibre GL for interactive maps, and Motion for animations from jsdelivr. These are standard, well-known services for web development.
  • [COMMAND_EXECUTION]: The skill includes a Node.js script, scripts/validate-swiss-deck.mjs, which the agent uses to verify the structure and design compliance of generated HTML files. This script performs static analysis via regular expressions and does not execute arbitrary code or perform unauthorized system actions.
  • [PROMPT_INJECTION]: The skill's instructions in SKILL.md are focused on design principles, layout selection, and user requirements gathering. No attempts to override agent safety protocols or bypass system constraints were detected.
  • [DATA_EXFILTRATION]: No data exfiltration logic was found. The skill processes information locally to generate static HTML files. The optional PPTX export feature uses the browser-side libraries PptxGenJS and html2canvas to generate files locally on the user's machine without transmitting data externally.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 02:10 PM
Security Audit — agent-trust-hub — guizang-ppt-skill