doordash-allergy-shield

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests outsider-authored free text via the dd-cli cart show output (menu item names/descriptions coming from DoorDash listings / potentially user-entered cart contents), which the vetting step then checks and writes into a vetted dump that the checkout hook reads.