spawn_command_runUnder

What spawn_command_runUnder does on Cobalt Strike MCP Server

AI agents invoke spawn_command_runUnder to trigger actions in Cobalt Strike MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why spawn_command_runUnder is rated High

This tool executes arbitrary commands under a specified process, which is a direct code/command execution capability. In the context of Cobalt Strike (a red team framework), this enables arbitrary command execution on compromised systems via beacon control. The blast radius is critical—an AI misusing this could execute malicious commands, exfiltrate data, establish persistence, or pivot through networks.

From the tool's definition Tool named 'spawn_command_runUnder' with description 'Run command under a process' in a Cobalt Strike red team operations server enabling beacon control and payload generation. Cobalt Strike is a post-exploitation framework used for adversarial operations.

The rule that runs spawn_command_runUnder safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Cobalt Strike MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For spawn_command_runUnder, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "spawn_command_runUnder": {
      "limits": [
        {
          "counter": "spawn_command_rununder_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about spawn_command_runUnder