appscript

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly shows runtime ingestion of untrusted third-party content — e.g., the "Web アプリ（Webhook エンドポイント）" doPost example (with webapp access ANYONE_ANONYMOUS) that parses incoming POST payloads, and multiple UrlFetchApp.fetch calls to external APIs (e.g., https://api.example.com/data) — both of which cause the script to read and act on arbitrary public/user-provided content.