google-sheets

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow only instructs the agent to call Google Sheets tools (e.g., google_sheets_values_get to read ranges like Sheet1!A1:Z5) and then write/verify; the sheet contents and headers are outsider-authored free text if the spreadsheet was not authored by the operating user, creating an indirect prompt-injection risk via LLM ingestion of those cell values.