Install an APK file on the device
AI agents invoke adb_install_app 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.
Installing an APK executes an external operation that deploys application code onto a device. This can introduce malicious software, bypass security controls, or establish persistence. It is not merely writing data — it triggers the Android package installer and grants the app permissions/capabilities on the device. The blast radius is high since a misused install could deploy malware or spyware.
From the tool's definition Install an APK file on the device
Attacks that exploit this kind of access
Install an APK file on the device. 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_install_app: 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_install_app 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_install_app 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_install_app. 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_install_app 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 →