Press the home button
AI agents invoke adb_press_home to trigger actions in Openclaw 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 an external operation on an Android device by simulating a home button press. It does not read data, write/create data persistently, delete anything, or involve finances. It is a device control action that navigates the UI state, fitting the Execute category. Severity is low because pressing home is a benign navigation action with minimal blast radius.
From the tool's definition Press the home button — triggers a physical device action via ADB (Android Debug Bridge), simulating a hardware button press on the connected Android device.
Attacks that exploit this kind of access
Press the home button. It is categorised as a Execute tool in the Openclaw Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Openclaw Adb MCP server in PolicyLayer and add a rule for adb_press_home: 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 Openclaw Adb. Nothing to install.
adb_press_home 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 adb_press_home 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 adb_press_home. 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.
adb_press_home is provided by the Openclaw Adb MCP server (wilsonbeam/openclaw-adb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →