xlsx

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process data from external spreadsheet files (XLSX, CSV, TSV). \n
  • Ingestion points: The skill reads external files using pd.read_excel() and load_workbook() as described in the workflows in SKILL.md. \n
  • Boundary markers: No boundary markers or specific safety instructions are provided to the agent to distinguish between cell data and potential malicious instructions. \n
  • Capability inventory: The environment allows for Python script execution, file system modification, and system command execution via the recalc.py script. \n
  • Sanitization: The skill does not implement or recommend sanitization for the data extracted from the spreadsheets before it is used by the agent. \n- [COMMAND_EXECUTION]: The recalc.py helper script performs local command execution and modifies application configuration files. \n
  • Evidence: The script uses subprocess.run to invoke the soffice (LibreOffice) binary in headless mode to recalculate formulas. \n
  • Evidence: It automatically writes a LibreOffice macro file (Module1.xba) to the user's application configuration directory (e.g., ~/.config/libreoffice/ or ~/Library/Application Support/LibreOffice/) to enable the recalculation functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:26 AM