frame-liquid-bg-hero
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches resources from well-known and trusted services:
- Loads Tailwind CSS via
https://cdn.tailwindcss.cominexample.html. - Loads fonts from Google Fonts via
https://fonts.googleapis.cominexample.html. - The instructions in
SKILL.mdsuggest usingjsdelivrfor optional WebGL libraries. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user-provided content (quotes and subtitles) to render them in the final HTML output:
- Ingestion points: User-supplied quotes and subtitles processed by the agent into the template.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill generates HTML/CSS/JS for visual preview; it does not perform network exfiltration or sensitive file operations.
- Sanitization: No specific sanitization or escaping of the user-provided text is documented.
Audit Metadata