skills/lifangda/claude-plugins/xlsx/Gen Agent Trust Hub

xlsx

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (MEDIUM): The script invokes soffice (LibreOffice) via subprocess.run. While it avoids shell injection by passing arguments as a list, executing a full office suite to process external files involves running a complex environment that could be targeted by document-based exploits.
  • [DYNAMIC_EXECUTION] (MEDIUM): The skill dynamically creates a LibreOffice Basic macro file (Module1.xba) in the user's application configuration directory at runtime. It then triggers this macro using a vnd.sun.star.script URI. Generating and executing script files at runtime is a sensitive pattern that can be used to bypass static analysis.
  • [PERSISTENCE_MECHANISMS] (LOW): The script modifies the persistent configuration of LibreOffice by creating or overwriting files in ~/.config/libreoffice or ~/Library/Application Support/LibreOffice. These changes persist on the host system after the skill has finished its task.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:42 PM