skills/opencoworkai/open-cowork/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes system utilities such as soffice (LibreOffice), Xvfb (virtual framebuffer), and timeout to perform headless formula recalculation. These commands are invoked using secure argument list patterns to prevent shell injection.
  • [COMMAND_EXECUTION]: The script modifies local user configuration by creating a LibreOffice Basic macro (Module1.xba) in the application's configuration directory. This is a documented, functional requirement for automating the workbook recalculation process.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external spreadsheets, which constitutes an indirect prompt injection surface.
  • Ingestion points: The skill uses pandas.read_excel and openpyxl.load_workbook to read content from user-supplied files.
  • Boundary markers: The instructions do not specify delimiters or warnings to ignore potential instructions embedded within the spreadsheet data.
  • Capability inventory: The skill can write to the file system and execute specific system commands via the recalculation script.
  • Sanitization: Data from cell contents is processed without explicit sanitization or filtering for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:28 AM