google-sheets-plg

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill reads existing spreadsheet data from the user-specified Google Sheet (outsider-authored cell contents) via the Sheets API and returns it in tool outputs that the agent/harness will include in the LLM context (free-text cell values / error messages), enabling indirect prompt injection.