skills/iliagerman/agents/docx/Gen Agent Trust Hub

docx

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'subprocess.run' API with list-based arguments to execute established system utilities. 'ooxml/scripts/pack.py' calls 'soffice' (LibreOffice) to validate produced Office files through HTML conversion, and 'ooxml/scripts/validation/redlining.py' uses 'git diff' to perform text diffing for redlining validation.
  • [EXTERNAL_DOWNLOADS]: The 'SKILL.md' file instructs the user to install well-known and trusted dependencies including 'pandoc', 'libreoffice', and the 'docx' NPM library from official repositories.
  • [PROMPT_INJECTION]: Documentation includes instructions like 'MANDATORY
  • READ ENTIRE FILE' and 'NEVER set any range limits'. These are evaluated as benign instructional directives intended to ensure the agent processes full contextual information for complex document manipulation tasks, rather than attempts to override safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 07:51 AM