skills/insight68/skills/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script recalc.py executes system binaries to perform spreadsheet operations via LibreOffice.\n
  • Evidence: The script utilizes subprocess.run to call soffice for headless spreadsheet processing, as well as timeout or gtimeout for process management.\n- [COMMAND_EXECUTION]: The script recalc.py dynamically writes a LibreOffice StarBasic macro to the local file system to enable formula recalculation.\n
  • Evidence: The setup_libreoffice_macro function creates or overwrites Module1.xba in the user's LibreOffice configuration directory.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from external spreadsheet files without sanitization.\n
  • Ingestion points: Data is loaded from user-provided files using pandas.read_excel and openpyxl.load_workbook as described in SKILL.md.\n
  • Boundary markers: No delimiters or specific safety instructions are used to distinguish between spreadsheet data and agent instructions.\n
  • Capability inventory: The agent has the ability to write files to the system and execute subprocesses through the provided recalculation script.\n
  • Sanitization: No mechanisms are present to validate or sanitize cell content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 02:02 PM