The Agent Skills Directory

[COMMAND_EXECUTION]: The script recalc.py uses subprocess.run to execute the soffice (LibreOffice) binary for formula recalculation.
[COMMAND_EXECUTION]: To facilitate recalculation, recalc.py dynamically writes a LibreOffice Basic macro (Module1.xba) to the user's application configuration directory and executes it via the system command line.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from external spreadsheet files without explicit sanitization or boundary markers.
Ingestion points: Data enters the agent context through pd.read_excel() and load_workbook() calls mentioned in SKILL.md.
Boundary markers: The skill does not implement delimiters or 'ignore' instructions to separate untrusted spreadsheet data from internal logic.
Capability inventory: The agent has the capacity to write files (wb.save, df.to_excel) and execute system commands via the recalc.py helper.
Sanitization: There is no evidence of data validation or content filtering for data extracted from spreadsheets.

xlsx