browser_iframe_eval

Evaluate JavaScript inside a specific iframe.

SERVERTermux Browser Pilot SOURCEsalviz/termux-browser-pilot

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/salviz-termux-browser-pilot/browser-iframe-eval.md

WHAT IT DOES

What browser_iframe_eval does on Termux Browser Pilot

AI agents invoke browser_iframe_eval to trigger actions in Termux Browser Pilot. 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.

RISK

Why browser_iframe_eval is rated High

This tool executes arbitrary JavaScript code within an iframe context in a real browser. Arbitrary code execution in a browser can perform any operation the browser is capable of — reading/writing DOM, exfiltrating data, making network requests, triggering downloads, etc.

From the tool's definition Evaluate JavaScript inside a specific iframe

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_iframe_eval safely

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

browser_iframe_eval Rate-limited

browser_iframe_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": {
    "browser_iframe_eval": {
      "limits": [
        {
          "counter": "browser_iframe_eval_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Termux Browser Pilot, apply this rule, and every browser_iframe_eval call is checked against it from then on.

FAQ

Questions about browser_iframe_eval

What does the browser_iframe_eval tool do? +

Evaluate JavaScript inside a specific iframe. It is categorised as a Execute tool in the Termux Browser Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_iframe_eval? +

Register the Termux Browser Pilot MCP server in PolicyLayer and add a rule for browser_iframe_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 Termux Browser Pilot. Nothing to install.

What risk level is browser_iframe_eval? +

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

Can I rate-limit browser_iframe_eval? +

Yes. Add a rate_limit block to the browser_iframe_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 browser_iframe_eval completely? +

Set action: deny in the PolicyLayer policy for browser_iframe_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 browser_iframe_eval? +

browser_iframe_eval is provided by the Termux Browser Pilot MCP server (salviz/termux-browser-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Termux Browser Pilot, and thousands of servers like it.

This server

All 148 Termux Browser Pilot tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →