design-prompt-generator-v2
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
sample/index.htmlfile includes a reference to a stylesheet from the jsDelivr Content Delivery Network (CDN) to load UI icons. - Evidence:
https://cdn.jsdelivr.net/npm/remixicon@4.1.0/fonts/remixicon.cssinsample/index.html. - Note: jsDelivr is a well-known service, and this reference is for standard font loading in a static sample file.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided service names, categories, and descriptions to generate output.
- Ingestion points: The
User Inputsection inSKILL.mdidentifies where user data enters the context. - Capability inventory: The skill does not possess any capabilities for file system access, network operations, or command execution.
- Boundary markers: The instructions do not define specific delimiters for user input.
- Sanitization: No explicit sanitization is described in the instructions.
- Risk assessment: Because the skill lacks any exploitable tools or capabilities, the indirect prompt injection surface is assessed as safe.
Audit Metadata