frame-logo-outro
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it interpolates user-supplied brand names, taglines, and metadata strings directly into a generated HTML and SVG template.
- Ingestion points: User-provided Brand name, Tagline, and CTA fields as defined in the skill documentation and example data.
- Boundary markers: Absent; the skill instructions do not specify the use of delimiters or specific prompts to prevent the agent from treating user data as executable instructions.
- Capability inventory: The skill is capable of generating and rendering HTML, CSS, and SVG, which could be used to execute arbitrary scripts if combined with malicious input.
- Sanitization: No sanitization, validation, or escaping mechanisms are described for the user-supplied input before it is placed into the code template.
- [EXTERNAL_DOWNLOADS]: The skill references and loads external assets from well-known services and design catalogs.
- Integrates the Tailwind CSS framework via cdn.tailwindcss.com.
- Loads typography from Google Fonts (fonts.googleapis.com).
- References design inspiration from HeyGen's Hyperframes catalog (hyperframes.heygen.com).
Audit Metadata