skills/openai/skills/spreadsheet/Gen Agent Trust Hub

spreadsheet

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution for Dependency Management: The skill instructions include commands for installing system-level dependencies and Python packages. While these include the use of sudo for package management (e.g., sudo apt-get install -y libreoffice poppler-utils), this is a standard procedure for environment preparation and is presented as a setup instruction rather than an automated background task.
  • Data Processing Surface: The skill is designed to read and process external spreadsheet files (.xlsx, .csv, .tsv). This represents an indirect prompt injection surface where content within a processed file could theoretically attempt to influence the agent's behavior. However, the skill focuses on structural and data-driven tasks (formatting, formulas, analysis) which limits the impact of such patterns.
  • Local File System Interaction: The skill defines specific directories for intermediate (tmp/spreadsheets/) and final (output/spreadsheet/) files. This is a positive security practice as it provides a predictable and contained area for file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:26 AM