databricks-apps

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch and use manifests from arbitrary templates (e.g., "databricks apps manifest --template <GIT_URL>") as a required part of the scaffolding workflow, which clearly ingests untrusted public third‑party content that can change scaffolding/--set decisions and thus influence subsequent actions.