skills/andrewhaward2310/.agents/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill relies on standard, industry-recognized libraries for document processing, such as 'python-pptx' for PowerPoint manipulation and 'playwright' for HTML rendering and layout extraction.
  • [SAFE]: XML processing in 'unpack.py' and 'pack.py' is secured using 'defusedxml', which effectively mitigates XML External Entity (XXE) and other XML-related vulnerabilities.
  • [SAFE]: Identified subprocess executions in 'thumbnail.py', 'pack.py', and 'redlining.py' are used for benign operations like PDF conversion, thumbnail generation, and text comparison via 'git diff'. These calls use sanitized or internal file paths.
  • [SAFE]: Headless browser usage in 'html2pptx.js' is limited to processing local HTML files generated by the agent for slide layout calculation, posing minimal security risk.
  • [SAFE]: The skill's instructions and scripts do not contain hardcoded credentials, unauthorized network exfiltration patterns, or instructions intended to bypass safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 06:19 PM
Security Audit — agent-trust-hub — pptx