feishu-sheets

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow calls Feishu Sheets API “read” (GET /sheets/v2/spreadsheets/{spreadsheet_token}/values/{range}) to ingest spreadsheet cell values from a user-provided spreadsheet_token/range, and those cell texts can be outsider-authored (e.g., posted by anyone with access to that sheet), making them LLM-readable at runtime.