shopify-admin-agentic-policy-readability

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime GraphQL query shop { shopPolicies { type body url } } ingests the store’s existing policy body text (which is outsider-authored content from the store/Shopify tenant, not authored by the operating user) into the agent’s LLM context for auditing/classification.