sub-agent-dispatch

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for the agents-mcp tool, which is fetched from the vendor's official GitHub repository (metyatech/agents-mcp).
  • [REMOTE_CODE_EXECUTION]: Setup procedures for the orchestration tool utilize npx to execute code directly from the vendor's remote repository branch (git+https://github.com/metyatech/agents-mcp.git#main).
  • [COMMAND_EXECUTION]: Detailed CLI commands are provided for adding MCP servers to Claude Code, Codex, and Gemini platforms. Additionally, the skill documents PowerShell workarounds using .NET classes ([IO.File]::Delete) to manage files in environments where standard cmdlets are restricted by policy.
  • [SAFE]: The skill implements a robust verification and review protocol. It includes templates for implementation and reviewer agents that enforce requirement verification and spec-alignment checks, mitigating risks associated with delegating tasks to autonomous sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 07:53 AM
Security Audit — agent-trust-hub — sub-agent-dispatch