frame-macos-notification

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches Tailwind CSS from cdn.tailwindcss.com and web fonts from fonts.googleapis.com within example.html. Both are well-known and standard services for web development.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate the notification content.
  • Ingestion points: SKILL.md instructs the agent to use user-provided content for the App name, Title, and Body fields.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are specified for the user input interpolation.
  • Capability inventory: The skill outputs HTML and CSS content intended for rendering.
  • Sanitization: There are no instructions to escape or sanitize the user-provided strings before they are inserted into the HTML structure, which could lead to layout disruption or injection if the output is rendered in a high-privilege environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:01 AM