product-frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data provided by the user, including live URLs and product copy, and use this data to generate frontend code.
- Ingestion points: The 'Scope' section specifies that users may provide live URLs, screenshots, and product copy for the agent to review.
- Capability inventory: The skill is instructed to generate implementation-grade frontend code (HTML/CSS/JS, React) based on this input.
- Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data to be analyzed and potential instructions hidden within that data.
- Sanitization: The instructions do not define any sanitization or validation steps for content fetched from external URLs before it is processed by the agent.
Audit Metadata