AI agents invoke browser_scroll to trigger actions in Apple Shortcuts. 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 a running browser session. It falls under the Execute category as it triggers an external browser operation. Severity is medium because misuse could be part of automated browser manipulation, though scrolling alone has limited blast radius.
From the tool's definition 'Scroll the page in a direction' — this is a browser action that manipulates the browser viewport state
Documented attack patterns abuse exactly the kind of access browser_scroll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_scroll:
{
"version": "1",
"default": "deny",
"tools": {
"browser_scroll": {
"limits": [
{
"counter": "browser_scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} browser_scroll 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.
Free to start. No card required.
Scroll the page in a direction. It is categorised as a Execute tool in the Apple Shortcuts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple Shortcuts 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 Apple Shortcuts. 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 Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Shortcuts, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
423 Apple Shortcuts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.