Your agent runs 24/7. Do you know what it's doing right now?
Agent Shield shows you everything your OpenClaw agent does, blocks dangerous actions before they execute, and masks your personal data. Set up in four steps: one package, two environment variables, one init command, one gateway restart.
The Morning After
You wake up. Your agent ran all night. Here's what happened:
Protection Rules, Activated at Setup
Every OpenClaw capability has a risk. Every risk has a shield.
The rule set lives on the Palveron server and is maintained there. Setup activates the baseline rules for your project and plan and reports how many are active. You can see, adjust and extend every rule in your dashboard.
Bring Your Own Model
You already have your own AI key, like every OpenClaw user. Agent Shield uses your key for the content checks. For you this means: Palveron adds no model costs of its own, and the checks work the same way on every plan.