cart-abandonment-recovery
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for processing potentially untrusted data, such as product names, quantities, and URLs from a shopping cart, and incorporating them into communication channels like email and SMS. While this is standard e-commerce functionality, it represents a surface where malicious input in a cart could attempt to influence the content of automated messages if the platform's rendering engine does not provide adequate sanitization.
- Ingestion points:
cart.items(includingProductName,ProductURL,ImageURL) andcart.customerEmailinSKILL.mdcode snippets. - Boundary markers: Absent in the example Typescript code snippets.
- Capability inventory:
fetch(network),db(database), andrecoveryQueue(scheduling). - Sanitization: Not explicitly implemented in the provided documentation examples, though typically handled by the recommended third-party platforms (Klaviyo, etc.).
Audit Metadata