html-ppt-retro-quarterly-review

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's HTML templates (example.html and assets/template.html) fetch external resources from well-known and reputable services.
  • Loads fonts from Google Fonts (fonts.googleapis.com and fonts.gstatic.com).
  • Loads the GSAP animation library from JSDelivr (cdn.jsdelivr.net).
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection by processing user-supplied data into HTML artifacts.
  • Ingestion points: Workflow step 1 in SKILL.md instructs the agent to map requested token changes into CSS variables.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Uses file_write to generate the final HTML artifact.
  • Sanitization: Instructions focus on preserving visual style rather than explicit input sanitization, though this is typical for presentation generation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 08:01 PM