load_script · Frida MCP: Risk & Policy

WHAT IT DOES

What load_script does on Frida

AI agents invoke load_script to trigger actions in Frida. 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 IT NEEDS A POLICY

Why load_script needs a policy

Loading and executing arbitrary JavaScript scripts into a live process via Frida constitutes code execution with significant blast radius. The script runs persistently inside a target process, enabling hooks, memory reads/writes, and RPC exports — any of which could be used to exfiltrate data, modify process behavior, or compromise system integrity.

From the tool's definition Load a persistent background Frida script... set up hooks that collect data over time or long-running RPC exports

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_script Rate-limited

load_script stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Frida, so you can run agents against it safely.

FAQ

Questions about load_script

What does the load_script tool do? +

Load a persistent background Frida script. Use this to set up hooks that collect data over time or long-running RPC exports. Afterwards, use. It is categorised as a Execute tool in the Frida MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on load_script? +

Register the Frida MCP server in PolicyLayer and add a rule for load_script: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Frida. Nothing to install.

What risk level is load_script? +

load_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit load_script? +

Yes. Add a rate_limit block to the load_script rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block load_script completely? +

Set action: deny in the PolicyLayer policy for load_script. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides load_script? +

load_script is provided by the Frida MCP server (snowluma/mcp-frida). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.