excel-automation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides functionality to execute VBA macros within Excel workbooks using the 'wb.macro()' interface and provides raw access to underlying system APIs (COM/AppleScript) via the '.api' property. This allows for the execution of embedded code or complex application control which could be leveraged if the workbook originates from an untrusted source.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Excel workbooks which can influence agent behavior. Ingestion points: Reading values from cells and ranges in SKILL.md via 'sheet.value', 'expand()', and 'used_range'. Boundary markers: The skill does not define specific delimiters or warnings for the agent when processing workbook content. Capability inventory: The skill has the ability to write files, execute macros, and manipulate the Excel application instance. Sanitization: There is no evidence of input validation or content filtering for data extracted from Excel.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of 'xlwings', a widely-used Python library for Excel automation. The instructions guide the user to install the package using standard tools ('pip install xlwings').
Audit Metadata