frame-logo-outro

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied data such as brand names and taglines to populate an HTML template.
  • Ingestion points: The SKILL.md file specifies that the agent must use user-provided brand names and taglines.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the user input are provided.
  • Capability inventory: The skill generates HTML, CSS, and SVG content for rendering a video-style outro.
  • Sanitization: There are no explicit instructions for sanitizing or escaping the user-provided strings before interpolation into the HTML structure.
  • [EXTERNAL_DOWNLOADS]: The example implementation fetches styling and typography resources from well-known services.
  • Evidence: The example.html file includes a script tag for cdn.tailwindcss.com and a link tag for fonts.googleapis.com to load the Inter and Noto Sans SC font families.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:56 PM
Security Audit — agent-trust-hub — frame-logo-outro