typespec-create-api-plugin

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to integrate with arbitrary external REST APIs (see actions.tsp @server("[API_BASE_URL]", ...) and the Workflow question "What is the API base URL and purpose?"), meaning the agent will fetch and interpret untrusted third‑party responses (and use them to drive reasoning and responses via @reasoning/@responding), which can enable indirect prompt injection.