make-scenario-building

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to call the Make public template library (public-templates_list and public-templates_get-blueprint in Phase 1 Step 2.5) to fetch and study public templates (user-visible blueprints) and then use those templates as structural reference for module selection and blueprint construction, meaning untrusted, user-generated content is ingested and can materially influence the agent's configuration and subsequent tool actions.