shopify-json-ld

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

• Third-party content exposure detected (high risk: 0.75). The required workflow fetches and then feeds outsider-authored free text into the agent’s LLM context via the “Fetch → Generate” pipeline, where the model is given product/page content (e.g., descriptionHtml, page/article copy) that originates from the store’s existing content rather than being authored by the operating user.