skills/bigdra50/skills/unilyze-setup/Gen Agent Trust Hub

unilyze-setup

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'unilyze' tool from an external repository using Homebrew (e.g., brew install bigdra50/tap/unilyze). This is a standard installation procedure for the documented tool.
  • [COMMAND_EXECUTION]: The skill makes extensive use of CLI commands for code analysis, configuration management, and report generation (e.g., unilyze -p <project>, unilyze config add-exclude-dir). These operations are consistent with the tool's primary purpose of static analysis.
  • [REMOTE_CODE_EXECUTION]: The skill contains commands that install additional agent-specific skills (unilyze skills install --claude) and register an MCP (Model Context Protocol) server (unilyze mcp). These actions facilitate deep integration with AI agents but involve the execution and installation of code from the vendor's distribution mechanism.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:15 PM
Security Audit — agent-trust-hub — unilyze-setup