execute_unlink

What execute_unlink does on Cobalt Strike MCP Server

AI agents invoke execute_unlink 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 execute_unlink is rated High

While not destructive to data (no irreversible deletion), unlinking a beacon is an Execute category action because it triggers an external operation (beacon disconnection) whose effects depend on which beacon is targeted. The severity is high due to the operational impact in a red team context—this can disrupt ongoing operations, alert defenders, or cause loss of access to compromised systems.

From the tool's definition Tool performs 'unlink from beacon' operation on an active Cobalt Strike beacon, which terminates the command and control relationship with a compromised host. This is an active operation that severs established C2 communication.

The rule that runs execute_unlink 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 execute_unlink, this is the rule to start with:

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

Questions about execute_unlink