execute_unlink · Cobalt Strike MCP Server MCP: Risk & Policy

WHAT IT DOES

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 IT NEEDS A POLICY

Why execute_unlink needs a policy

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.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_unlink Rate-limited

execute_unlink stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Cobalt Strike MCP Server, so you can run agents against it safely.

FAQ

Questions about execute_unlink

What does the execute_unlink tool do? +

Unlink from beacon. It is categorised as a Execute tool in the Cobalt Strike MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_unlink? +

Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for execute_unlink: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cobalt Strike MCP Server. Nothing to install.

What risk level is execute_unlink? +

execute_unlink is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_unlink? +

Yes. Add a rate_limit block to the execute_unlink rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block execute_unlink completely? +

Set action: deny in the PolicyLayer policy for execute_unlink. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides execute_unlink? +

execute_unlink is provided by the Cobalt Strike MCP Server MCP server (mickeydb/cobalt-strike-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.