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

docx

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess.run to invoke system binaries such as soffice for document validation and git for change comparison. These calls are executed using argument lists rather than shell strings, which prevents command injection risks.
  • [EXTERNAL_DOWNLOADS]: The documentation guides users to install the docx library from the npm registry, a standard and well-known dependency for Node.js-based document generation.
  • [SAFE]: The skill processes external document data (ingestion points located in scripts/unpack.py and scripts/ooxml/scripts/unpack.py). While document text is not wrapped in explicit boundary markers, the vulnerability surface is secured. Capabilities are restricted to local file manipulation and designated validation tools. Sanitization is consistently applied through secure XML parsing using defusedxml and directory-bound checks during the extraction of ZIP archive contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:29 AM