run_pacu

What run_pacu does on Pentester-MCP

AI agents invoke run_pacu 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_pacu is rated High

PACU (Privilege Escalation and AWS Credential Utility) is a pentest tool that autonomously exploits AWS infrastructure through API calls, credential theft, and privilege escalation. Execution capability is confirmed by the server context. Even sandboxed execution of such tools poses critical risk if an AI agent misuses it against unintended targets, escalates privileges unexpectedly, or exfiltrates credentials.

From the tool's definition Tool is part of Pentester-MCP server which enables execution of '200+ open-source penetration testing tools' including 'reconnaissance, web exploitation, and brute-forcing.' PACU is an AWS exploitation framework that executes arbitrary AWS API calls and…

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

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

Questions about run_pacu