xlsx-official

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script utilizes the subprocess.run function to execute system commands. It invokes the soffice (LibreOffice) binary in headless mode to run a Basic macro for formula recalculation and manages execution using the timeout or gtimeout utilities.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface as it is designed to ingest and interpret data from external Excel workbooks.
  • Ingestion points: Data enters the agent's context via pandas.read_excel() and openpyxl.load_workbook() operations mentioned in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within spreadsheet cells are provided in the instructions.
  • Capability inventory: The skill has the capability to modify the local filesystem (writing Excel files) and execute shell commands through the recalc.py script.
  • Sanitization: The skill does not implement validation or sanitization of the content read from Excel files before processing or displaying it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 11:36 AM
Security Audit — agent-trust-hub — xlsx-official