google-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill reads and imports Google Docs content (e.g., the "Read Document" operation and read_document()/export_document() that fetch content from URLs like https://docs.google.com/document/d/[DOCUMENT_ID]/edit), which can be arbitrary, user-generated third-party content and thus could carry indirect prompt-injection instructions.