shopify-api
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Shopify APIs, which introduces a potential surface for indirect prompt injection. 1. Ingestion points: Product, order, and customer data is retrieved from the Shopify GraphQL Admin API, REST Admin API, and Storefront API endpoints as documented in SKILL.md. 2. Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are provided to isolate retrieved content from the agent's prompt context. 3. Capability inventory: The skill demonstrates network access to myshopify.com domains and the ability to read or modify product, order, and customer resources. 4. Sanitization: While the skill includes basic error handling for API responses, it does not provide specific patterns for sanitizing external string content (such as product descriptions or customer metafields) before it is processed by an LLM.
Audit Metadata