ppt-keynote
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references styling and typography assets from well-known services, including the Tailwind CSS CDN and Google Fonts, to render the slide visuals.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a content transformer that ingests user-supplied text to generate HTML outputs, creating a surface where malicious instructions in the input could potentially influence the output generation.
- Ingestion points: User-provided markdown or text content (e.g., example.md) used to populate the slide templates.
- Boundary markers: The skill does not currently specify the use of delimiters or specific boundary instructions to isolate user content within the generator prompt.
- Capability inventory: The skill is capable of generating HTML structures and client-side JavaScript for navigation (e.g., keyboard event listeners).
- Sanitization: No explicit sanitization or escaping protocols for user data are defined in the SKILL.md instructions before the content is injected into the HTML section elements.
Audit Metadata