shopify-admin-agentic-metafields-setup

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

• Third-party content exposure detected (high risk: 0.75). Runtime GraphQL products query ingests outsider-authored product content from the store’s catalog (e.g., descriptionHtml, tags, options) into the agent’s LLM context for inference, which can include text authored by parties other than the operating user.