dom_eval · Hermes Computer Use MCP: Risk & Policy

WHAT IT DOES

What dom_eval does on Hermes Computer Use

AI agents invoke dom_eval to trigger actions in Hermes Computer Use. 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 dom_eval needs a policy

This tool executes arbitrary JavaScript directly in the browser page context, giving an AI agent unrestricted code execution capabilities including DOM manipulation, data exfiltration, network requests, and interaction with any page APIs. The word 'arbitrary' confirms there are no restrictions on what code can be run, making this a critical-severity Execute tool.

From the tool's definition 'Evaluate arbitrary JavaScript in the page context'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dom_eval Rate-limited

dom_eval 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": {
    "dom_eval": {
      "limits": [
        {
          "counter": "dom_eval_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 Hermes Computer Use, so you can run agents against it safely.

FAQ

Questions about dom_eval

What does the dom_eval tool do? +

Evaluate arbitrary JavaScript in the page context and return the. It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on dom_eval? +

Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for dom_eval: 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 Hermes Computer Use. Nothing to install.

What risk level is dom_eval? +

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

Can I rate-limit dom_eval? +

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

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

dom_eval is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.