frame-light-leak-cinema
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references styling and font assets from well-known services, specifically Tailwind CSS via
cdn.tailwindcss.comand typography fromfonts.googleapis.com. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to populate HTML templates with user-provided content, which introduces an indirect prompt injection surface.
- Ingestion points: User-provided titles, subtitles, and metadata fields (year, chapter, location) described in
SKILL.md. - Boundary markers: No boundary markers or instructions to ignore embedded instructions are present in the skill files.
- Capability inventory: The skill generates and renders HTML/CSS code as seen in
example.html. - Sanitization: There are no explicit instructions for sanitizing or escaping the user-provided input before it is interpolated into the HTML template.
Audit Metadata