building-storefronts
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from custom API routes, creating a standard surface where external content enters the application context.
- Ingestion points: Data returned from
sdk.client.fetch()inSKILL.mdandreferences/frontend-integration.mdwhich is then processed by React Query. - Boundary markers: None are explicitly defined in the provided implementation templates.
- Capability inventory: The skill utilizes the Medusa JS SDK for network operations and data fetching.
- Sanitization: The instructions focus on state management and SDK patterns without explicitly detailing input validation or output encoding for the external data.
Audit Metadata