OpenClaw Integration

Rafter integrates seamlessly with OpenClaw to add security to autonomous coding agents.

Setup

1. Install Rafter CLI

Install globally:

npm install -g @rafter-security/cli

2. Initialize Agent Security

Run initialization (auto-detects OpenClaw):

rafter agent init

If OpenClaw is detected, Rafter will:

✓ Install skill to ~/.openclaw/skills/rafter-security.md
✓ Enable agent integration in config
✓ Set up security policies

3. Restart OpenClaw

Restart OpenClaw to load the Rafter skill:

# Stop OpenClaw
openclaw stop

# Start OpenClaw
openclaw start

How It Works

Once integrated, OpenClaw agents automatically use Rafter for security-sensitive operations:

User → OpenClaw Agent → Rafter Security → Safe Execution

Example Flow

User request:

"Commit these changes to git"

OpenClaw processes:

Generates commit message
Calls Rafter: rafter agent exec "git commit -m '...'"
Rafter scans staged files for secrets
If clean: Executes commit
If secrets found: Blocks and alerts user

Skill Commands

The Rafter skill provides these commands to OpenClaw:

`/rafter-scan`

Scan files for secrets before operations. When OpenClaw uses it:

Before git commits
When reading sensitive files
After generating code with credentials

Example:

User: "Is there anything sensitive in this codebase?"
OpenClaw: rafter agent scan .

`/rafter-bash`

Execute shell commands with validation. When OpenClaw uses it:

For any shell command execution
Before destructive operations
When using sudo

Example:

User: "Install the dependencies"
OpenClaw: rafter agent exec "npm install"

`/rafter-audit`

View security event logs. When OpenClaw uses it:

After blocked commands
When reviewing security events
For compliance reporting

Example:

User: "Show me recent security events"
OpenClaw: rafter agent audit --last 10

Configuration

Risk Levels for OpenClaw

Choose based on your use case:

Minimal (Development)

Best for: Local development, prototyping

rafter agent config set agent.riskLevel minimal

Allows most commands
Basic secret detection
Minimal interruption to workflow

Moderate (Recommended)

Best for: General use, team environments

rafter agent config set agent.riskLevel moderate

Blocks critical commands
Requires approval for high-risk operations
Secret scanning on all git operations
Default setting

Aggressive (Production)

Best for: Sensitive environments, compliance requirements

rafter agent config set agent.riskLevel aggressive

Maximum security checks
Requires approval for most operations
Comprehensive audit logging
Best for production agents

Command Policy

Control how commands are handled:

# Default: Approve dangerous commands
rafter agent config set agent.commandPolicy.mode approve-dangerous

# Alternative: Block specific patterns only
rafter agent config set agent.commandPolicy.mode deny-list

# Permissive: Allow all (not recommended)
rafter agent config set agent.commandPolicy.mode allow-all

Usage Examples

Safe Development Workflow

User: "Create a new feature for user authentication"

OpenClaw:
Generates code
Runs rafter agent scan  # Check for secrets
If clean, proceeds
Creates git commit with rafter agent exec
Scans staged files again
Commits successfully

Blocked Dangerous Operation

User: "Clean up all files in the project"

OpenClaw generates: rm -rf /

Rafter:
🚫 Command BLOCKED
Risk Level: CRITICAL
Reason: Matches blocked pattern: rm -rf /

OpenClaw: "This command is too dangerous. Please specify which files to delete."

Approval Required

User: "Force push to main branch"

OpenClaw generates: git push --force origin main

Rafter:
⚠️  Command requires approval
Risk Level: HIGH
Approve this command? (yes/no):

User: no

OpenClaw: "Command cancelled. Would you like to push normally instead?"

Best Practices

Recommended Setup

Start with moderate risk level: Adjust based on experience
Review audit logs daily: rafter agent audit --last 20
Train agents on Rafter commands: Ensure agents know when to use security checks
Test policies in development: Before deploying to production
Keep Rafter updated: npm update -g @rafter-security/cli

Monitoring

View Agent Activity

Check what your agent is doing:

# Recent command executions
rafter agent audit --event command_intercepted

# Secret detections
rafter agent audit --event secret_detected

# Filter by agent
rafter agent audit --agent openclaw --last 50

Audit Reports

Generate reports for compliance:

# Export last 7 days as JSON
rafter agent audit --since $(date -v-7d +%Y-%m-%d) --json > agent-audit.json

Troubleshooting

Skill Not Loading

If OpenClaw doesn’t recognize Rafter commands:

Check skill file exists:

ls ~/.openclaw/skills/rafter-security.md

Reinstall skill:
```
rafter agent init --force
```
Restart OpenClaw:
```
openclaw restart
```

Commands Not Being Validated

If commands bypass Rafter:

Check config:

rafter agent config get agent.environments.openclaw.enabled
# Should be: true

Verify policy mode:

rafter agent config get agent.commandPolicy.mode

Enable if disabled:

rafter agent config set agent.environments.openclaw.enabled true

False Positives

If safe commands are being blocked:

Check audit log:
```
rafter agent audit --last 5
```

Adjust risk level:

rafter agent config set agent.riskLevel minimal

Report issue: rafter-cli/issues

Advanced Configuration

Custom Blocked Patterns

Add organization-specific patterns: Edit ~/.rafter/config.json:

{
  "agent": {
    "commandPolicy": {
      "blockedPatterns": [
        "rm -rf /",
        "kubectl delete namespace production",
        "terraform destroy"
      ]
    }
  }
}

Approval Patterns

Require approval for specific commands:

{
  "agent": {
    "commandPolicy": {
      "requireApproval": [
        "git push --force",
        "npm publish",
        "docker push.*production"
      ]
    }
  }
}

Multi-Agent Setup

Running multiple OpenClaw instances:

# Each agent gets same config by default
# Customize per-agent if needed:

# Agent 1 (aggressive)
export RAFTER_RISK_LEVEL=aggressive
openclaw start --name agent1

# Agent 2 (moderate)
export RAFTER_RISK_LEVEL=moderate
openclaw start --name agent2

Get Started

CLI Guides

Agent Security

References

​OpenClaw Integration

​Setup

​1. Install Rafter CLI

​2. Initialize Agent Security

​3. Restart OpenClaw

​How It Works

​Example Flow

​Skill Commands

​/rafter-scan

​/rafter-bash

​/rafter-audit

​Configuration

​Risk Levels for OpenClaw

​Command Policy

​Usage Examples

​Safe Development Workflow

​Blocked Dangerous Operation

​Approval Required

​Best Practices

Recommended Setup

​Monitoring

​View Agent Activity

​Audit Reports

​Troubleshooting

​Skill Not Loading

​Commands Not Being Validated

​False Positives

​Advanced Configuration

​Custom Blocked Patterns

​Approval Patterns

​Multi-Agent Setup

​Support

Need Help?

​Next Steps

Command Reference

Secret Scanning

OpenClaw Integration

Setup

1. Install Rafter CLI

2. Initialize Agent Security

3. Restart OpenClaw

How It Works

Example Flow

Skill Commands

`/rafter-scan`

`/rafter-bash`

`/rafter-audit`

Configuration

Risk Levels for OpenClaw

Command Policy

Usage Examples

Safe Development Workflow

Blocked Dangerous Operation

Approval Required

Best Practices

Monitoring

View Agent Activity

Audit Reports

Troubleshooting

Skill Not Loading

Commands Not Being Validated

False Positives

Advanced Configuration

Custom Blocked Patterns

Approval Patterns

Multi-Agent Setup

Support

Next Steps