deck-swiss-international
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external assets including CSS and font files from well-known services.
https://cdn.tailwindcss.com(Tailwind CSS framework)https://fonts.googleapis.com(Google Fonts service)- [REMOTE_CODE_EXECUTION]: The example HTML includes a script tag to load the Tailwind CSS CDN, which is a standard practice for development and prototyping using well-known services.
- Evidence:
<script src="https://cdn.tailwindcss.com"></script>inexample.html. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content to generate a structured HTML deck. This ingestion of untrusted data represents a potential surface for indirect prompt injection, though the risk is low and inherent to the skill's primary purpose.
- Ingestion points: User-provided text content processed through the templates defined in
SKILL.md. - Boundary markers: The skill uses bracketed headers (e.g.,
【模板】,【布局】) to structure instructions and delimit content sections. - Capability inventory: Generates static HTML/CSS output; no dangerous command execution or network capabilities detected.
- Sanitization: No explicit content sanitization logic is described in the prompt instructions.
Audit Metadata