AI agents invoke arrow_down to trigger actions in DrissionPageMCP. 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.
This tool triggers a browser action (sending a keypress event to a browser tab), which is an external operation affecting the browser's state. It falls under Execute as it performs a browser interaction. The blast radius is low since it only sends a scroll/navigation keypress with minimal side effects.
From the tool's definition 向当前标签页发送按键 arrow_down (sends arrow_down keypress to current tab)
Documented attack patterns abuse exactly the kind of access arrow_down gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DrissionPageMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for arrow_down:
{
"version": "1",
"default": "deny",
"tools": {
"arrow_down": {
"limits": [
{
"counter": "arrow_down_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}arrow_down 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.
向当前标签页发送按键 arrow_down. It is categorised as a Execute tool in the DrissionPageMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DrissionPage MCP server in PolicyLayer and add a rule for arrow_down: 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 DrissionPageMCP. Nothing to install.
arrow_down 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 arrow_down 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 arrow_down. 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.
arrow_down is provided by the DrissionPage MCP server (wxhzhwxhzh/drissionpagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 37 DrissionPageMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
37 DrissionPageMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.