skills/smallnest/langgraphgo/xlsx/Gen Agent Trust Hub

xlsx

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [Dynamic Execution] (MEDIUM): The script recalc.py dynamically generates a StarBasic macro (Module1.xba) and writes it to the local filesystem before instructing LibreOffice to execute it. This involves runtime script generation and execution.
  • [Persistence Mechanisms] (MEDIUM): To enable recalculation, the script installs a persistent macro into the user's LibreOffice configuration directory (e.g., ~/.config/libreoffice/4/user/basic/Standard/). This modification remains active across system restarts and application sessions.
  • [Indirect Prompt Injection] (LOW): The skill processes external Excel files, which presents an attack surface for indirect injection.
  • Ingestion points: Reads workbook content via the openpyxl library in recalc.py.
  • Boundary markers: None are applied to cell contents during error scanning.
  • Capability inventory: The skill can execute local binaries via subprocess.run and modify application configuration files.
  • Sanitization: No sanitization is performed on the strings extracted from the workbook cells before they are included in the output summary.
  • [Command Execution] (LOW): The script executes the soffice binary and system timeout utilities using subprocess.run. While it follows best practices by using argument lists instead of shell strings, it still interacts with the local operating system.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:41 AM