docx
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes system utilities like soffice (LibreOffice) and git via subprocess.run. These calls are used for document format validation and text comparison (redlining), which are central to the skill's documented purpose. The calls are constructed using lists rather than shell strings, mitigating command injection risks.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing necessary system dependencies such as pandoc, libreoffice, and poppler-utils using the system package manager. These are legitimate tools required for document processing.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to process external document files, it has an ingestion surface for untrusted data. However, it employs the defusedxml library for all XML parsing, which provides protection against XML External Entity (XXE) and other XML-based injection attacks.
- [SAFE]: Analysis of the skill's instructions, metadata, and scripts revealed no signs of prompt injection, data exfiltration, or obfuscation. The behavior matches the stated purpose of professional document manipulation.
Audit Metadata