Excel Automation
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from external spreadsheet sources which may contain untrusted content.\n
- Ingestion points: Data is retrieved from Microsoft Excel and Google Sheets using the
GOOGLESHEETS_BATCH_GETtool as documented in the workflow sections.\n - Boundary markers: The instructions lack specific delimiters or boundary markers to prevent the agent from obeying instructions that might be contained within the spreadsheet data.\n
- Capability inventory: The agent is granted capabilities to write, update, and format spreadsheet data, as well as create and upload new workbooks.\n
- Sanitization: There is no evidence of data sanitization or validation to filter out executable-like text or prompt injection patterns from the ingested spreadsheet cells.
Audit Metadata