frame-macos-notification
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches external assets from well-known and trusted services, specifically loading fonts from Google Fonts (fonts.googleapis.com) and utilizing the Tailwind CSS CDN (cdn.tailwindcss.com) for layout and styling components.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to populate an HTML notification template, creating a surface for potential injection if the input contains malicious markup.
- Ingestion points: User-provided Title and Body fields defined in the skill instructions.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat input as literal text only.
- Capability inventory: The skill generates an HTML file capable of executing CSS and potentially JavaScript within the user's browser or preview environment.
- Sanitization: There are no instructions for the agent to sanitize, escape, or validate the user-provided content before rendering.
Audit Metadata