sheetsu

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Proxy requests" and "Connecting to Sheetsu" instructions show it uses the Membrane connector to fetch data from the Sheetsu/Google Sheets API (via membrane request and action runs), which will return arbitrary, user-generated spreadsheet content from third-party sources that the agent is expected to read and could influence its actions.