document-docx

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted .docx files, creating a potential surface for indirect prompt injection.
  • Ingestion points: The scripts docx_extract.py, docx_quality_gate.py, and docx_to_html.mjs ingest external document content.
  • Boundary markers: A security warning comment is injected into the HTML output by docx_to_html.mjs.
  • Capability inventory: The skill utilizes subprocess.run for conversion tasks and performs file writes.
  • Sanitization: The documentation explicitly instructs users to sanitize extracted content before further use.
  • [DYNAMIC_EXECUTION]: The docx_quality_gate.py script invokes LibreOffice via subprocess.run for document conversion. This is performed using a secure argument list pattern and is central to the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill includes documentation and scripts for executing command-line operations related to Word document processing and conversion.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:02 PM