pptx

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external .pptx files, creating a potential surface for indirect instructions.
  • Ingestion points: SKILL.md describes using python-pptx and pandoc to extract text and structure from presentations.
  • Boundary markers: The instructions do not explicitly mandate delimiters or specific "ignore" instructions for the extracted text.
  • Capability inventory: The skill has file-writing capabilities via python-pptx and shell execution capabilities via pandoc and LibreOffice.
  • Sanitization: Content is extracted and processed without explicit sanitization or validation steps mentioned in the documentation.
  • [EXTERNAL_DOWNLOADS]: Documents dependencies on standard libraries like python-pptx and pandoc (SKILL.md). These are well-known, established tools for document processing.
  • [COMMAND_EXECUTION]: Uses shell commands including pandoc, soffice, and pdftoppm for document conversion and extraction tasks, which is consistent with its intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:07 PM
Security Audit — agent-trust-hub — pptx