deck-swiss-international
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content (text and data) and transforms it into an HTML slide deck. Because the instructions do not specify any sanitization or escaping protocols for this user data, there is a risk that malicious instructions or scripts embedded in the input could be executed when the generated deck is viewed in a browser.\n
- Ingestion points: User-provided content intended for slides as described in the YAML frontmatter and instructions.\n
- Boundary markers: The instructions do not define delimiters or protective warnings to prevent the agent from following instructions embedded within the user data.\n
- Capability inventory: The skill generates HTML files with embedded CSS and interactive features like keyboard navigation and hash synchronization.\n
- Sanitization: No instructions are provided to validate or sanitize the user-supplied strings before they are interpolated into the generated HTML structure.\n- [EXTERNAL_DOWNLOADS]: The example HTML file includes a reference to the Tailwind CSS CDN, which is a well-known service for front-end styling.
Audit Metadata