xlsx

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes the soffice (LibreOffice) binary and system timeout utilities. These commands are used to perform formula recalculations in Excel files.
  • [COMMAND_EXECUTION]: recalc.py programmatically generates a LibreOffice Basic macro file (Module1.xba) within the user's application configuration directory. This macro is a functional requirement to automate the "calculate and save" workflow in a headless environment.
  • [PROMPT_INJECTION]: The skill processes untrusted data from spreadsheet files (XLSX, CSV, TSV), which creates a surface for indirect prompt injection if cell contents contain malicious instructions.
  • Ingestion points: Data is loaded via pd.read_excel and load_workbook (recalc.py, SKILL.md).
  • Boundary markers: No specific delimiters are defined to isolate untrusted cell data from the agent's instructions.
  • Capability inventory: The skill can execute subprocesses (recalc.py) and perform file system writes (wb.save, df.to_excel).
  • Sanitization: No explicit validation or sanitization of spreadsheet cell content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:53 PM
Security Audit — agent-trust-hub — xlsx