google-docs

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

• Third-party content exposure detected (high risk: 0.90). This SKILL.md explicitly instructs the agent to fetch and read arbitrary Google Docs via the Docs API (e.g., "Get Document Content" / "Extract Plain Text" using https://docs.googleapis.com/v1/documents/{document-id}), so untrusted user-generated document content can be ingested and used to compute indexes and drive batchUpdate operations that influence subsequent actions.