skills/ymx10086/researchclaw/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/recalc.py executes the soffice (LibreOffice) binary using subprocess.run. This is used to programmatically recalculate spreadsheet formulas and is an expected part of the skill's utility.
  • [EXTERNAL_DOWNLOADS]: The skill documentation indicates a dependency on LibreOffice (soffice) and git. It recommends installing LibreOffice via system package managers if it is missing.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external Excel files.
  • Ingestion points: Excel files are loaded via pandas.read_excel and openpyxl.load_workbook (referenced in SKILL.md).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The agent can execute shell commands via scripts/recalc.py and write files to the file system.
  • Sanitization: No specific sanitization or validation of the input file content is performed before processing style and conventions.
  • [PERSISTENCE_MECHANISMS]: The scripts/recalc.py script writes a LibreOffice Basic macro (RecalculateAndSave.xba) to the user's application configuration directory (e.g., ~/.config/libreoffice/). This ensures the recalculation functionality is available to the office suite across sessions.
  • [DYNAMIC_EXECUTION]: The skill generates and writes an XML-based macro file at runtime and then instructs LibreOffice to execute that macro. This is used strictly for the purpose of updating Excel formula values.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 06:26 AM