Google ADK integration

Action security for Google ADK.

Install action checks on an ADK agent’s runtime hooks.

Get the package and source.

Connect the execution boundary.

Install the firewall before running the agent. Validate callback behaviour against the deployed ADK release and the tools in use.

An example to test

A service agent attempts to export metadata after reading untrusted context. Evaluate the action at the hooked tool boundary.

Illustrative workflow, not a customer deployment or a measured result.

Before connecting live policy

  1. Identify the handler that actually performs the side effect.
  2. Provide trusted identity, purpose and final action arguments.
  3. Configure the tenant’s assigned runtime and keep API credentials server-side.
  4. Test allowed, blocked and unavailable paths before production.

Integration example

Adapt this existing SDK pattern to your application. Names such as the agent, handler and session refer to your own objects. Follow the package documentation for compatible versions and complete setup.

# Install Google ADK support.
python -m pip install "agenticdome-python-sdk[google-adk]"

from agenticdome_sdk.google_adk import AgenticDomeGoogleADKFirewall

firewall = AgenticDomeGoogleADKFirewall()
firewall.install_on_agent(agent)

agenticdome-demo --framework google-adk --scenario metadata_exfil

Python demo commands evaluate fixed inputs against a bundled local policy; they do not instantiate the selected framework or prove a live integration. The TypeScript client and OpenClaw runtime plugin need their documented tenant configuration.

See the decision before the action.

Try a local scenario, then bring your workflow to a deployment review. Start with one agent and one tool, and see exactly where the action can be stopped.