deck-guizang-editorial
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's sample implementation references styling and typography resources from well-known services.\n
- Fetches the Tailwind CSS framework from
cdn.tailwindcss.comto handle dynamic slide layout.\n - Loads specialized font families (Playfair Display, Inter, Noto Serif SC, Noto Sans SC) from Google Fonts (
fonts.googleapis.com).\n- [INDIRECT_PROMPT_INJECTION]: The skill functions as a template for user-provided data, creating a potential surface for indirect prompt injection.\n - Ingestion points: User-supplied text is ingested to populate the 10 layout types defined in
SKILL.md.\n - Boundary markers: Absent. The instructions do not provide explicit delimiters or specific warnings to ignore instructions embedded in the user content.\n
- Capability inventory: The skill generates HTML and CSS that is rendered within the agent's presentation surface.\n
- Sanitization: No explicit logic is defined to sanitize or validate external content before it is interpolated into the HTML structure.
Audit Metadata