inject_hook · JS Reverse MCP: Risk & Policy

WHAT IT DOES

What inject_hook does on JS Reverse MCP

AI agents invoke inject_hook to trigger actions in JS Reverse 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 IT NEEDS A POLICY

Why inject_hook needs a policy

Hook injection is a form of code execution: it modifies the runtime behavior of a live browser page by inserting intercepting code. This falls under Execute (running code/browser actions) rather than Write, since the primary effect is runtime code execution and behavior modification, not data persistence.

From the tool's definition 'Inject an existing hook into the current page' — injecting hooks into a browser page executes code within the page context, triggering external operations whose effects depend on the hook being injected.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

inject_hook Rate-limited

inject_hook 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": {
    "inject_hook": {
      "limits": [
        {
          "counter": "inject_hook_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 JS Reverse MCP, so you can run agents against it safely.

FAQ

Questions about inject_hook

What does the inject_hook tool do? +

Inject an existing hook into the current page. It is categorised as a Execute tool in the JS Reverse MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on inject_hook? +

Register the JS Reverse MCP server in PolicyLayer and add a rule for inject_hook: 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 JS Reverse MCP. Nothing to install.

What risk level is inject_hook? +

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

Can I rate-limit inject_hook? +

Yes. Add a rate_limit block to the inject_hook 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 inject_hook completely? +

Set action: deny in the PolicyLayer policy for inject_hook. 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 inject_hook? +

inject_hook is provided by the JS Reverse MCP server (noone-hub/jsreverser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.