xlsx

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes the soffice (LibreOffice) binary using subprocess.run to perform formula recalculation in a headless environment. This is a functional requirement for updating spreadsheet values without user interaction.
  • [DYNAMIC_EXECUTION]: The recalc.py script generates a LibreOffice Basic macro (Module1.xba) and writes it to the user's application configuration directory (e.g., ~/.config/libreoffice/ or ~/Library/Application Support/LibreOffice/). This macro is used to automate the 'calculate all' and 'save' commands within the spreadsheet application.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Excel, CSV, and TSV files using libraries like pandas and openpyxl.
  • Ingestion points: Data enters the agent's context through pd.read_excel() and load_workbook() calls documented in SKILL.md.
  • Boundary markers: The skill does not explicitly define delimiters for untrusted data in its examples.
  • Capability inventory: The skill has capabilities to write to the filesystem (macro configuration) and execute system binaries (soffice).
  • Sanitization: The recalc.py script performs post-calculation verification by scanning for Excel formula errors (e.g., #REF!, #DIV/0!), providing a basic level of integrity checking for the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:02 PM