wmill-native-trigger

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

• Third-party content exposure detected (high risk: 0.90). The skill requires ingesting and processing arbitrary external webhook payloads and API responses from third-party services (e.g., Nextcloud/Google) as part of its runtime flow—see the External::prepare_webhook signature (headers, body) and the testing checklist item "Webhook receives and processes payloads" in SKILL.md—so untrusted third-party content can influence runtime behavior.