AI agents invoke swipe_down to trigger actions in Adb. 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 executes a UI input action (swipe gesture) on a remote Android device. It causes an external operation whose effects depend on the current screen state. It is not purely reading data, and while reversible in nature, it falls under Execute as it triggers device interaction. Severity is low since a swipe gesture has limited blast radius, though it could inadvertently interact with on-screen elements.
From the tool's definition swipe_down: 在屏幕上向下滑动 (swipe down on the screen) — triggers a physical gesture/input action on an Android device via ADB
Documented attack patterns abuse exactly the kind of access swipe_down gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adb, and nothing reaches the server without passing your rules. This is the rule we recommend for swipe_down:
{
"version": "1",
"default": "deny",
"tools": {
"swipe_down": {
"limits": [
{
"counter": "swipe_down_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}swipe_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.
在屏幕上向下滑动. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb MCP server in PolicyLayer and add a rule for swipe_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 Adb. Nothing to install.
swipe_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 swipe_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 swipe_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.
swipe_down is provided by the Adb MCP server (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, 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.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.