excel-automation

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides functional code examples for executing VBA macros within Microsoft Excel workbooks using the wb.macro() method. It also includes methods for application control, such as suppressing system alerts (app.display_alerts = False) and modifying screen updating behavior.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the xlwings library using the standard Python package manager (pip install xlwings). This is a well-known library for Excel automation.
  • [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface because it is designed to ingest and process data from external, potentially untrusted Excel files.
  • Ingestion points: Excel cell values (sheet['A1'].value), ranges (sheet.used_range.value), and VBA code modules (wb.api.VBProject.VBComponents('Module1').CodeModule.Lines) are read into the agent context.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are included in the prompt templates when reading cell content.
  • Capability inventory: The skill allows the agent to execute code (VBA macros), save files (wb.save), and export documents (ExportAsFixedFormat).
  • Sanitization: There is no evidence of sanitization or validation of the data read from the Excel files before it is processed or used to influence agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — excel-automation