AI agents invoke browser_navigate to trigger actions in Byob. 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.
Navigation to an arbitrary URL in a logged-in browser session is an Execute-class action: it triggers external operations (HTTP requests, page loads, script execution) whose effects depend entirely on the URL argument. An AI agent given this tool could navigate to malicious sites, trigger unintended API calls, or exploit authenticated sessions.
From the tool's definition Tool performs 'navigate to the URL' which triggers browser navigation and page load actions with side effects dependent on the URL argument.
Attacks that exploit this kind of access
Open a new tab (or reuse a given tabId) and navigate to the URL. It is categorised as a Execute tool in the Byob MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Byob MCP server in PolicyLayer and add a rule for browser_navigate: 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 Byob. Nothing to install.
browser_navigate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser_navigate 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.
Set action: deny in the PolicyLayer policy for browser_navigate. 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.
browser_navigate is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.