skills/2898117012/agent-skills/docx/Gen Agent Trust Hub

docx

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (MEDIUM): The validate_document function in ooxml/scripts/pack.py uses subprocess.run to call the soffice (LibreOffice) binary. This execution occurs on documents generated from XML files that may have been modified or provided by untrusted sources, creating a risk if soffice has vulnerabilities.
  • [DATA_EXPOSURE] (HIGH): The ooxml/scripts/unpack.py script uses zipfile.ZipFile.extractall() without verifying that the paths within the ZIP archive are safe. A malicious Office document could include filenames with ../ to perform a Zip Slip attack, overwriting sensitive files on the host system.
  • [INDIRECT_PROMPT_INJECTION] (MEDIUM): The skill's primary function is to process untrusted external data (OOXML files). In ooxml/scripts/validation/docx.py, lxml.etree.parse is used to process these XML files without explicit hardening against XML External Entity (XXE) or expansion attacks, which could lead to resource exhaustion or information disclosure.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:12 PM