xlsx
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runinrecalc.pyto invokesoffice(LibreOffice) for formula recalculation. This is a legitimate functional requirement of the skill and is performed on local files using a predefined command structure. The use ofgtimeoutortimeoutis also handled appropriately for cross-platform support. - [EXTERNAL_DOWNLOADS]: No external downloads or remote script executions were identified. The skill relies on locally installed software (LibreOffice, Python libraries like pandas and openpyxl).
- [PROMPT_INJECTION]: The
SKILL.mdfile contains instructions for the AI to follow specific formatting and calculation standards (e.g., Financial Model standards). These are benign operational guidelines and do not attempt to bypass safety filters or override system instructions. - [DATA_EXFILTRATION]: There are no network operations or suspicious file access patterns that would indicate data exfiltration. The skill focuses on reading and writing local
.xlsxand.csvfiles. - [DYNAMIC_EXECUTION]: No
eval(),exec(), or unsafe deserialization patterns were found. Code generation is restricted to standard Python scripts for spreadsheet manipulation.
Audit Metadata