skills/ali156666/panda-bot/xlsx/Gen Agent Trust Hub

xlsx

Warn

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (MEDIUM): The script uses subprocess.run in recalc.py to invoke system binaries including soffice (LibreOffice), timeout, and gtimeout. While it avoids shell=True, it relies on external system-level execution capabilities.\n- DYNAMIC_EXECUTION (MEDIUM): The script dynamically generates a StarBasic macro file (Module1.xba) and writes it to the user's application configuration directory (~/Library/Application Support/LibreOffice/4/user/basic/Standard or ~/.config/libreoffice/4/user/basic/Standard). It subsequently executes this generated code via the vnd.sun.star.script URI. This pattern modifies the local application environment and introduces runtime-generated executable logic.\n- INDIRECT_PROMPT_INJECTION (LOW): The skill processes untrusted Excel files which serves as an attack surface for indirect injection.\n
  • Ingestion points: recalc.py accepts a filename via sys.argv[1] and parses it using openpyxl.\n
  • Boundary markers: None present.\n
  • Capability inventory: The script can execute system commands and modify application configuration files.\n
  • Sanitization: There is no validation of the filename or cell content before it is passed to subprocesses or processed by the macro engine.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 03:56 AM