guizang-ppt-skill

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill templates and components reference assets from trusted and well-known content delivery networks (CDNs). These include:
  • Lucide icons from unpkg.com.
  • The Motion One animation library from jsdelivr.net.
  • MapLibre GL from unpkg.com for geographic components.
  • Typography assets from fonts.googleapis.com.
  • [COMMAND_EXECUTION]: The workflow documentation in SKILL.md describes the use of standard shell commands for project setup and management. These include:
  • mkdir and cp for creating directories and copying template files.
  • node scripts/validate-swiss-deck.mjs to execute a local validation script that checks the generated HTML file for design rule compliance.
  • open to preview the resulting presentation in a web browser.
  • [PROMPT_INJECTION]: The skill uses templates where user-provided text and image paths are interpolated into the generated HTML. While this represents a surface for indirect prompt injection (where data becomes instructions), the skill does not contain instructions to bypass agent safety filters or access sensitive system data, and it relies on the model's standard output filters during the generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 12:27 PM
Security Audit — agent-trust-hub — guizang-ppt-skill