skills/itzfaisal/content-studio/docx/Gen Agent Trust Hub

docx

Warn

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the subprocess module to execute external binaries, including soffice (LibreOffice), git, and gcc across multiple scripts (scripts/accept_changes.py, scripts/office/soffice.py, and scripts/office/validators/redlining.py).
  • [DYNAMIC_EXECUTION]: In scripts/office/soffice.py, the skill dynamically generates C source code, writes it to a temporary location, and compiles it into a shared object (.so) file using gcc. This library is then injected into the LibreOffice process using the LD_PRELOAD environment variable to shim network socket behavior. While this appears to be a functional workaround for sandbox limitations, it is a high-risk process injection technique.
  • [COMMAND_EXECUTION]: The script scripts/accept_changes.py generates and executes a StarBasic macro within the LibreOffice environment to automate document changes, which involves executing arbitrary code within the Office suite context.
  • [EXTERNAL_DOWNLOADS]: The documentation in SKILL.md instructs the user to perform a global installation of a Node.js package (npm install -g docx), which introduces an external dependency into the execution environment.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 09:59 PM
Security Audit — agent-trust-hub — docx