pptx

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external binaries for document processing and validation tasks.
  • Evidence: Scripts such as thumbnail.py, pack.py, and validate.py invoke soffice (LibreOffice), pdftoppm (Poppler), and git using subprocess.run.
  • Context: These utilities are standard for document conversion and comparison. The execution uses safe list-based arguments which prevents shell command injection.
  • [EXTERNAL_DOWNLOADS]: The documentation identifies several reputable third-party dependencies required for the skill's functionality.
  • Evidence: SKILL.md specifies markitdown, pptxgenjs, playwright, and sharp as required dependencies.
  • Context: These tools are well-known libraries within the document processing and web rendering ecosystems.
  • [SAFE]: The toolkit follows established security best practices for handling untrusted document data.
  • Evidence: The implementation utilizes defusedxml in unpack.py and pack.py to protect against XML External Entity (XXE) attacks when processing Office Open XML content.
  • Context: The inclusion of these security measures demonstrates an intentional effort to handle user-supplied files safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:43 AM
Security Audit — agent-trust-hub — pptx