run_ssh_command

What run_ssh_command does on Pentester-MCP

AI agents invoke run_ssh_command 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_ssh_command is rated High

This tool runs commands on remote systems via SSH. Even though the description is empty, the name and server context make clear it executes arbitrary shell commands, which is an Execute-category capability. Severity is high because SSH command execution can compromise remote systems, exfiltrate data, or enable lateral movement—though the blast radius depends on target permissions and network exposure.

From the tool's definition Tool name 'run_ssh_command' indicates execution of arbitrary commands over SSH; server description confirms it enables 'autonomous execution' of penetration testing tools; sibling tools like 'execute_weevely_module' and 'generate_weevely_agent' establish this…

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

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

Questions about run_ssh_command