skills/jd-opensource/joysafeter/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution] (SAFE): The skill uses subprocess.run to call soffice (LibreOffice) and system timeout utilities. These calls use list-based arguments, which prevents shell injection vulnerabilities. This behavior is essential for the skill's purpose of automating Excel recalculation.
  • [Dynamic Execution] (SAFE): The skill generates a StarBasic macro file (Module1.xba) and stores it in the LibreOffice user profile directory. While this constitutes dynamic code generation, the macro content is hardcoded, benign, and restricted to calculating and saving the document.
  • [Indirect Prompt Injection] (SAFE): The skill processes external Excel files, which represents a potential ingestion surface for untrusted data.
  • Ingestion points: recalc.py reads cell data using the openpyxl library to scan for Excel errors.
  • Boundary markers: Absent; however, the skill does not interpret cell content as instructions.
  • Capability inventory: File system access and subprocess execution (soffice).
  • Sanitization: The script treats cell values strictly as strings for comparison against static error codes (e.g., '#VALUE!'), preventing any execution of content found within the spreadsheet cells.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 05:57 PM