skills/mxyhi/ok-skills/minimax-xlsx/Gen Agent Trust Hub

minimax-xlsx

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/xlsx_insert_row.py uses subprocess.run to execute the internal utility script xlsx_shift_rows.py. This is used to coordinate complex row-shifting logic across multiple XML files.
  • [COMMAND_EXECUTION]: The script scripts/libreoffice_recalc.py uses subprocess.run to invoke the soffice (LibreOffice) binary for headless spreadsheet recalculation. This is an essential feature for ensuring formula cache integrity in generated files.
  • [DATA_EXFILTRATION]: The skill's primary purpose involves reading and writing files on the local filesystem. These operations are performed as part of the requested spreadsheet tasks and are scoped to the project environment.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (Excel and CSV files) and has significant filesystem and command execution capabilities. This represents an indirect prompt injection surface. However, the skill implements sanitization using standard XML and HTML escaping libraries throughout its script suite.
  • Ingestion points: scripts/xlsx_reader.py using pandas.read_excel and pandas.read_csv on user-supplied files.
  • Boundary markers: Not explicitly defined in instructions.
  • Capability inventory: Extensive filesystem access (read/write) and shell command execution via subprocess.run (scoped to internal scripts and LibreOffice).
  • Sanitization: Uses xml.etree.ElementTree, xml.dom.minidom, and html.escape to sanitize data written into XML structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:51 AM