Install and configure the ClawGuard security plugin - an LLM-as-a-Judge guardrail that detects and blocks risky tool calls
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
ClawGuard is a security plugin that uses an LLM-as-a-Judge to evaluate tool calls before execution, detecting and optionally blocking risky operations.
Before installing ClawGuard, ensure the gateway's chat completions endpoint is enabled:
openclaw config set gateway.http.endpoints.chatCompletions.enabled true
Install the plugin from npm:
openclaw plugins install @capsulesecurity/clawguard
After installation, restart the gateway to load the plugin.
If running OpenClaw in Docker:
# Install the plugin docker compose run --rm openclaw-cli plugins install @capsulesecurity/clawguardRestart gateway with force-recreate to reload env vars
docker compose up -d --force-recreate openclaw-gateway
Important: Always use
--force-recreatedocker compose restartCheck the gateway logs for the initialization message:
[clawguard] Initialized (logging: true, security: true, block: true, metrics: enabled)
Configure ClawGuard via
openclaw config set plugins.clawguard.<option> <value>| Option | Default | Description |
|---|---|---|
| enabled | true | Enable/disable the plugin |
| logToolCalls | true | Log tool call JSON to gateway logs |
| securityCheckEnabled | true | Run LLM security evaluation |
| blockOnRisk | true | Block high/critical risk tool calls |
| maxContextWords | 2000 | Session context word limit for evaluation |
| timeoutMs | 15000 | Security check timeout in milliseconds |
| gatewayHost | 127.0.0.1 | Gateway host for LLM calls |
| gatewayPort | 18789 | Gateway port for LLM calls |
| metricsEnabled | true | Enable anonymous usage metrics |
# Disable blocking (log-only mode) openclaw config set plugins.clawguard.blockOnRisk falseIncrease timeout for slower models
openclaw config set plugins.clawguard.timeoutMs 30000
Disable metrics collection
openclaw config set plugins.clawguard.metricsEnabled false
ClawGuard calls the gateway's
/v1/chat/completionsCheck the gateway token in your environment matches the config:
# Check env var printenv OPENCLAW_GATEWAY_TOKENCheck config token
cat ~/.openclaw/openclaw.json | grep -A2 '"token"'
If tokens don't match, update your environment and restart the gateway.
For Docker, ensure
.envOPENCLAW_GATEWAY_TOKEN--force-recreateThe chat completions endpoint is not enabled. Run:
openclaw config set gateway.http.endpoints.chatCompletions.enabled true
Token mismatch between environment and config. See Gateway Authentication section above.
openclaw plugins listClawGuard registers a
before_tool_calllogToolCallsblockOnRiskThe security evaluation uses your configured LLM provider, so it works with any model you have set up in OpenClaw.
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.