skills/modu-ai/moai-cowork/doc-docx/Gen Agent Trust Hub

doc-docx

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill refers to using the libreoffice command-line tool to perform PDF conversions of generated documents (libreoffice --headless --convert-to pdf output.docx). This is a standard and expected operation for a document generation workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content to populate document templates, presenting a surface for indirect prompt injection if the input contains malicious instructions. * Ingestion points: User input for document content as specified in SKILL.md. * Boundary markers: Structured document layouts and templates provided in references/modern-templates.md. * Capability inventory: Uses python-docx for document creation and shell execution for PDF conversion via libreoffice. * Sanitization: Employs a QA checklist in references/qa-checklist.md to identify unreplaced placeholders and filter 'AI slop' phrases.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 11:40 PM