Scroll the page or a specific element into view. Use when the user wants to scroll down a long page, scroll to the bottom, scroll to the top, or scroll a specific element into the viewport. With a ref, scrolls the element into view. Without a ref, scrolls the page by one viewport height or to a s...
AI agents invoke pilot_scroll to trigger actions in 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.
Scrolling is a browser interaction/action executed against a live browser session. It has no direct data read/write side effects, but it does execute an operation in an external browser environment. Severity is low because scrolling itself has minimal blast radius — it cannot directly cause data loss or financial harm — but it is an Execute action as it manipulates browser state.
From the tool's definition 'Scroll the page or a specific element into view' — triggers a browser action (scrolling) in a live Chromium instance via Playwright
Documented attack patterns abuse exactly the kind of access pilot_scroll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for pilot_scroll:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_scroll": {
"limits": [
{
"counter": "pilot_scroll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}pilot_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 or a specific element into view. Use when the user wants to scroll down a long page, scroll to the bottom, scroll to the top, or scroll a specific element into the viewport. With a ref, scrolls the element into view. Without a ref, scrolls the page by one viewport height or to a specific position. Parameters: - ref: Element reference from snapshot (e.g.,. It is categorised as a Execute tool in the Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pilot MCP server in PolicyLayer and add a rule for pilot_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 Pilot. Nothing to install.
pilot_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 pilot_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 pilot_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.
pilot_scroll is provided by the Pilot MCP server (tacosyhorchata/pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 61 Pilot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
61 Pilot tools catalogued and risk-classified — across an index of 42,500+ MCP servers.