document-converter

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell command templates for tools such as LibreOffice, pdftk, and ImageMagick to process files. If user-supplied filenames are not properly handled by the agent, this could lead to command injection vulnerabilities.
  • [PRIVILEGE_ESCALATION]: Documentation within the skill directs the agent to suggest commands involving sudo to users for the purpose of installing software dependencies on Linux systems.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external document files (PDFs, Office files, and images) which may contain embedded instructions intended to deceive the agent.
  • Ingestion points: User-provided files intended for conversion or OCR as described in SKILL.md.
  • Boundary markers: Absent. No specific delimiters or safety instructions are provided to help the agent distinguish between its instructions and the content of the documents.
  • Capability inventory: The skill has access to shell execution for tool invocation and filesystem write capabilities for output.
  • Sanitization: Absent. The instructions do not specify any validation or sanitization for document content or metadata.
  • [EXTERNAL_DOWNLOADS]: The skill refers users to well-known document processing utilities and provides installation instructions for official repositories using standard package managers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 09:49 AM