prototype-prompt-generator
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input to generate a complex prompt for downstream consumption. This surface area for indirect prompt injection is inherent to the skill's primary function.
- Ingestion points: User requirements gathered in 'SKILL.md' (Step 1).
- Boundary markers: Prompt templates in 'references/prompt-structure.md' use markdown structure and code blocks, though they lack explicit instructions for the consumer to ignore embedded commands.
- Capability inventory: The skill generates code-centric prompts including HTML structure and Tailwind CSS configurations.
- Sanitization: No explicit sanitization of user-provided content is performed before interpolation into the generated prompt.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for including well-known Content Delivery Networks (CDNs) such as Tailwind CSS ('https://cdn.tailwindcss.com') and FontAwesome in the resulting prototype code.
Audit Metadata