designing-banners
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes well-known and trusted external services for styling and typography, specifically Tailwind CSS via its official CDN and Google Fonts.
- [SAFE]: Package dependencies are managed through the official npm registry, requiring the standard 'playwright' library for headless browser rendering.
- [DYNAMIC_EXECUTION]: The skill generates HTML files based on templates and then renders them into PNG images using a headless browser script. This involves creating and processing web content dynamically at runtime, which is standard for the banner generation workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface where user-provided text is interpolated into HTML templates for banner creation.
- Ingestion points: Headline and message text fields within the HTML template structure in SKILL.md.
- Boundary markers: None explicitly defined in the provided template code.
- Capability inventory: The workflow executes local scripts via
node(scripts/render-to-png.js) which interact with the file system to save rendered images. - Sanitization: No explicit sanitization or escaping of the user-provided strings is documented within the skill instructions.
Audit Metadata