stop_sniffer

What stop_sniffer does on Pentester-MCP

AI agents invoke stop_sniffer 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 stop_sniffer is rated High

While the tool itself performs a cleanup/termination action, it still executes system-level operations (killing processes) whose effects depend on which PID is targeted. Misuse could terminate critical processes. However, it is not Destructive (data is not deleted/overwritten), not Financial, and not merely Read/Write. It is Execute because it triggers external system operations via process control.

From the tool's definition Tool terminates a background sniffing process using its Process ID (PID). The description indicates it performs process management/termination on the host system, which is an operational action that triggers external system effects.

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

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

Questions about stop_sniffer