shopify-admin-agentic-llms-txt

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context via the products query step: it fetches title and description from Shopify products (which may contain user/customer-authored content) and then step 3 renders those fields into the generated llms.txt that is fed back into the agent’s context for output/upsert.