skills/alijilani-dev/claude/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local system tools to perform document management tasks. These operations are essential for the presentation management workflow and are conducted safely on local files.
  • The thumbnail.py and pack.py scripts execute soffice and pdftoppm for slide conversion and validation.
  • The redlining.py script executes git diff for comparing document revisions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided PowerPoint files (.pptx), which is a document processing attack surface. The skill manages this risk through the following:
  • Ingestion points: Data from presentations is extracted via markitdown and python-pptx (in inventory.py).
  • Capability inventory: The skill can write XML files and execute local binary utilities (documented in pack.py and thumbnail.py).
  • Sanitization: Employs defusedxml in unpack.py and pack.py for secure XML parsing to prevent entity-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:31 PM
Security Audit — agent-trust-hub — pptx