ppt-keynote
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references Tailwind CSS via its official CDN (cdn.tailwindcss.com) and fetches typography from Google Fonts (fonts.googleapis.com). These are well-known services and are used for standard styling purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted markdown content into a formatted HTML slide deck.
- Ingestion points: Content provided by the user is interpolated into the HTML structure defined by the template (SKILL.md, example.html).
- Boundary markers: The template does not implement specific boundary markers or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill is restricted to frontend rendering and basic DOM-based keyboard navigation for slide transitions. It does not have access to sensitive tools such as file system writing, network exfiltration, or shell command execution.
- Sanitization: The template does not explicitly sanitize the user-provided input before rendering.
Audit Metadata