gdpr-ecommerce
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill guides the implementation of endpoints for Subject Access Requests and marketing consent that ingest untrusted user input, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the context through the request intake endpoint in pages/api/gdpr/request.ts and marketing opt-in forms.
- Boundary markers: The instructions do not specify the use of strict boundary markers or delimiters to isolate untrusted user data from the agent's internal instruction context.
- Capability inventory: The system is designed to perform database writes for data anonymization, send emails via SendGrid, and notify third-party processors like Klaviyo and Zendesk.
- Sanitization: The implementation criteria in evals/sar-export-api-and-marketing-consent/criteria.json require identity verification via email tokens before processing requests, which provides a layer of validation for external input.
- [EXTERNAL_DOWNLOADS]: The skill suggests installing GDPR-compliant tools and plugins from well-known platform marketplaces, including the Shopify App Store, WordPress Plugin Directory, and BigCommerce App Marketplace. These references target official and well-known services for store management.
Audit Metadata