office-academic-skill

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill extracts and processes text from untrusted academic documents (PDFs and LaTeX files) to generate presentations and reports.
  • Ingestion points: The references/thesis-defense-pptx/scripts/extract_thesis_context.py script uses PyMuPDF and pypdf to read external document content.
  • Boundary markers: Extraction scripts do not consistently apply delimiters or instructions to ignore embedded commands when inserting untrusted text into the agent's context.
  • Capability inventory: The skill has extensive file system access, document manipulation capabilities, and the ability to execute local commands.
  • Sanitization: No specific filtering or sanitization of the extracted text is performed before it is interpolated into prompts.
  • [COMMAND_EXECUTION]: Several Python and PowerShell scripts execute external binaries and system tools to perform document processing tasks.
  • The pack.py script in both Word and PowerPoint modules executes soffice (LibreOffice) to validate document integrity.
  • The thumbnail.py script executes soffice for PDF conversion and pdftoppm for slide image generation.
  • The redlining.py script executes git diff to provide character-level comparison between document versions.
  • [DYNAMIC_EXECUTION]: The skill uses automation technologies that execute code or content at runtime to generate documents.
  • The references/office-pptx/scripts/html2pptx.js script uses the Playwright library to launch a Chromium browser and render HTML templates.
  • PowerShell scripts located in references/thesis-defense-pptx/scripts/ utilize COM objects to automate Microsoft PowerPoint for slide cloning and export.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:10 PM