frame-macos-notification

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the Tailwind CSS Play CDN (cdn.tailwindcss.com) and Google Fonts (fonts.googleapis.com) to render the notification UI. These are well-known services used for front-end development and do not represent a security risk in this context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as application names, notification titles, and message bodies to populate the HTML template.
  • Ingestion points: Data enters the template via the SKILL.md instructions which guide the agent on how to use user content.
  • Boundary markers: None explicitly defined in the template structure.
  • Capability inventory: The skill generates HTML/CSS for rendering within a local preview environment. No file-write or network-write capabilities are requested.
  • Sanitization: There are no specific sanitization instructions for the user input; however, the scope is limited to UI generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:56 PM
Security Audit — agent-trust-hub — frame-macos-notification