run_pywhisker

What run_pywhisker does on Pentester-MCP

AI agents invoke run_pywhisker to trigger actions in Pentester-MCP. 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 run_pywhisker is rated High

Pywhisker exploits AD CS (Active Directory Certificate Services) by manipulating certificate attributes to escalate privileges or move laterally in Windows environments. This is not a read operation (no mere data retrieval), not a write operation (effects extend beyond simple data modification), and not destructive in the traditional sense, but it is an Execute category tool because it triggers external security…

From the tool's definition Tool name 'run_pywhisker' combined with server context as a penetration testing MCP that 'enables AI assistants to autonomously execute over 200 open-source penetration testing tools' including 'web exploitation' and 'brute-forcing'.

The rule that runs run_pywhisker safely

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

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

Questions about run_pywhisker