skills/practicalswan/agent-skills/doc/Gen Agent Trust Hub

doc

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses system tools for document processing.
  • The bundled Python script scripts/render_docx.py safely executes soffice (LibreOffice) by passing arguments as a list to subprocess.run, which prevents shell command injection.
  • The SKILL.md file contains standard shell command examples for rendering documents with soffice and pdftoppm.
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for standard and reputable software.
  • Python packages mentioned include python-docx and pdf2image from standard registries.
  • System tools include libreoffice and poppler-utils from official package managers.
  • [SAFE]: No malicious patterns such as obfuscation, credential harvesting, or unauthorized data exfiltration were identified. The skill correctly utilizes temporary directories for its intermediate rendering steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:07 PM
Security Audit — agent-trust-hub — doc