deploy-app

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

• Third-party content exposure detected (high risk: 1.00). The skill's required Phase 1 Research explicitly instructs invoking the kubesearch skill and running helm search hub (and references searching grafana.com and public OCI/Helm registries), which fetch and ingest public/community third‑party content that the agent is expected to read and use to decide chart vs app‑template and next actions.