google-sheets

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads spreadsheet contents from public Google Sheets endpoints (e.g., the "Read Cell Values" and "Read Entire Sheet" calls to https://sheets.googleapis.com/v4/spreadsheets/{spreadsheet-id}/values/...), which are user/third-party generated data that the agent is expected to parse and act on (search, update, append), so untrusted content can materially influence subsequent actions.