AI agents invoke browser_scroll 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.
Scrolling is a browser interaction/action that affects the state of the browser viewport. It falls under Execute as it triggers an external browser operation, though its blast radius is low since it only affects page position without reading sensitive data or modifying content.
From the tool's definition 'Scroll the page to a position, an element, or absolute Y coordinate' — triggers a browser action on a real Chrome browser
Attacks that exploit this kind of access
Scroll the page to a position, an element, or absolute Y coordinate. 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_scroll: 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_scroll 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_scroll 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_scroll. 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_scroll 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.