AI agents invoke browser_click 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.
Clicking elements in a real browser can trigger arbitrary actions: form submissions, purchases, deletions, navigation, downloads, etc. The effect depends entirely on what element is clicked, making this an Execute-category tool with high severity since it operates on real logged-in browser sessions and can cause significant side effects.
From the tool's definition Click an element matching the given CSS selector in the active browser tab
Attacks that exploit this kind of access
Click an element matching the given CSS selector in the active browser tab. 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_click: 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_click 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_click 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_click. 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_click 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.