setup-k8s-backend

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required workflow ingests outsider-authored free text at runtime by executing observe datastream list | wrap ... and observe content ... view | wrap ..., where datastream/content names and metadata may be set by any tenant write user and are then pasted back for parsing.