skills/openai/skills/slides/Gen Agent Trust Hub

slides

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • System Command Execution: The skill utilizes system utilities such as LibreOffice (soffice), Inkscape, and Ghostscript to perform document conversion and image rendering. These operations are conducted securely by passing arguments as lists to the subprocess handler and employing safety flags like -dSAFER for Ghostscript, which reduces the risk of command injection.
  • Data Ingestion and Processing: The skill is designed to process PowerPoint files (.pptx) and other media assets. It performs these tasks using established libraries (e.g., python-pptx, Pillow) and cleans up intermediate artifacts using temporary directories, ensuring that the processing environment remains secure and isolated.
  • Trusted Dependency Integration: The skill incorporates several standard libraries for specialized tasks, such as prismjs for syntax highlighting and mathjax-full for LaTeX rendering. These dependencies are well-maintained and are used within the scope of the skill's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 02:04 AM