working-with-spreadsheets
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to read and process external Excel files, creating a surface where untrusted data could influence agent behavior.
- Ingestion points: Data is ingested from external .xlsx files using
pandas.read_excelandopenpyxl.load_workbookas documented inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or guidance for the agent to ignore or isolate instructions that might be embedded within spreadsheet cells.
- Capability inventory: The skill demonstrates file system write capabilities using
wb.save()and command execution for verification viapython scripts/verify.py. - Sanitization: There is no evidence of data sanitization or validation logic to check the content of cells before they are processed or written to new files.
Audit Metadata