writer

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of standard document processing libraries from the Python Package Index (PyPI).
  • Evidence: pip install odfpy and pip install ezodf in SKILL.md.
  • [COMMAND_EXECUTION]: The skill utilizes system commands to automate LibreOffice and manage document archives.
  • Evidence: Use of soffice, unzip, zip, and killall via shell and Python's subprocess module in SKILL.md.
  • [PROMPT_INJECTION]: The template generation logic creates a surface for indirect prompt injection if untrusted data is interpolated into document XML.
  • Ingestion points: template_path and variables dictionary in the generate_from_template function in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: subprocess.run and soffice commands used for file processing and conversion in SKILL.md.
  • Sanitization: No explicit sanitization or escaping is performed on the variables before they are inserted into the document's XML structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:08 AM
Security Audit — agent-trust-hub — writer