native-trigger

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

• Third-party content exposure detected (high risk: 0.90). The skill's External trait implementations and workflow (e.g., create/update/get/list_all/maintain_triggers and prepare_webhook) explicitly fetch and reconcile data from external service APIs and accept webhook payloads via oauth_data.base_url and generated webhook URLs, meaning the agent will read and act on untrusted third‑party content from external services/webhooks.