spawn_and_inject

What spawn_and_inject does on Frida Agent MCP

AI agents invoke spawn_and_inject to trigger actions in Frida Agent 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 spawn_and_inject is rated High

Spawning a process and injecting code (e.g., Frida scripts) into it is a code execution action. In a dynamic analysis/reverse engineering context, this allows arbitrary code to run inside target application processes. The description is empty, but the name and server context make the intent clear. Misuse could allow injecting malicious scripts into any running Android app, making severity critical.

From the tool's definition Tool name 'spawn_and_inject' combined with server context: 'inject scripts, manage application processes' and sibling tools like 'execute', 'kill_app', 'launch_app' strongly imply spawning a process and injecting code into it.

The rule that runs spawn_and_inject safely

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

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

Questions about spawn_and_inject