🐾 OpenClaw Integration
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. One command. Zero config.
$ clawhub install agent-shield📋
The Morning After
You wake up. Your agent ran all night. Here's what happened:
847
Tool calls last night
3
Blocked (dangerous)
47
PII instances masked
$2.40
Estimated LLM cost
8 Shield Rules, Activated Instantly
Every OpenClaw capability has a risk. Every risk has a shield.
API key in promptBLOCK + Alert
rm -rf or destructive cmdBLOCK
PII in outputANONYMIZE
Hate speech / ToS violationBLOCK
Bulk file deletionREQUIRE_APPROVAL
Network exfiltrationBLOCK + Log
Package install (npm/pip)LOG + Alert
Social media postingREVIEW
Bring Your Own Model
You already have an LLM API key, every OpenClaw user does. agent-shield uses YOUR key for AI-powered policy evaluation. Our LLM cost: zero. Full 2-pass engine (regex + AI) included in every tier.