openclaw-warden-pro

# OpenClaw Warden Pro

Everything in [openclaw-warden](https://github.com/AtlasPA/openclaw-warden) (free) plus automated countermeasures.

**Free version detects threats. Pro version responds to them.**

## Detection Commands (also in free)

```bash
python3 {baseDir}/scripts/integrity.py baseline --workspace /path/to/workspace
python3 {baseDir}/scripts/integrity.py verify --workspace /path/to/workspace
python3 {baseDir}/scripts/integrity.py scan --workspace /path/to/workspace
python3 {baseDir}/scripts/integrity.py full --workspace /path/to/workspace
python3 {baseDir}/scripts/integrity.py status --workspace /path/to/workspace
python3 {baseDir}/scripts/integrity.py accept SOUL.md --workspace /path/to/workspace
```

## Pro Countermeasures

### Restore from Snapshot

Restore a tampered file to its baseline snapshot. Critical, config, and skill files are automatically snapshotted when the baseline is established.

```bash
python3 {baseDir}/scripts/integrity.py restore SOUL.md --workspace /path/to/workspace
```

### Git Rollback

Restore a file to its last git-committed state.

```bash
python3 {baseDir}/scripts/integrity.py rollback SOUL.md --workspace /path/to/workspace
```

### Quarantine a Skill

Disable a suspicious skill by renaming its directory. The agent will not load quarantined skills.

```bash
python3 {baseDir}/scripts/integrity.py quarantine bad-skill --workspace /path/to/workspace
```

### Unquarantine a Skill

Restore a quarantined skill after investigation.

```bash
python3 {baseDir}/scripts/integrity.py unquarantine bad-skill --workspace /path/to/workspace
```

### Protect (Automated Response)

Full scan + automatic countermeasures in one pass: restore tampered critical files, quarantine malicious skills, flag remaining issues. This is the recommended command for session startup.

```bash
python3 {baseDir}/scripts/integrity.py protect --workspace /path/to/workspace
```

## Recommended Integration

### Session Startup Hook (Claude Code)

```json
{
  "hooks"...

# OpenClaw Warden Pro

Full workspace security suite for [OpenClaw](https://github.com/openclaw/openclaw), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), and any Agent Skills-compatible tool.

Everything in [openclaw-warden](https://github.com/AtlasPA/openclaw-warden) (free) **plus automated countermeasures**: snapshot restore, skill quarantine, git rollback, and one-command protection sweeps.

## Free Version Detects. Pro Version Responds.

| Feature | Free | Pro |
|---------|------|-----|
| Baseline checksums | Yes | Yes |
| Integrity verification | Yes | Yes |
| Injection scanning | Yes | Yes |
| **Snapshot restore** | - | **Yes** |
| **Git rollback** | - | **Yes** |
| **Skill quarantine** | - | **Yes** |
| **Automated protect** | - | **Yes** |
| **Session startup hook** | - | **Yes** |

## Install

```bash
# Clone
git clone https://github.com/AtlasPA/openclaw-warden-pro.git

# Copy to your workspace skills directory
cp -r openclaw-warden-pro ~/.openclaw/workspace/skills/
```

## Usage

```bash
# Establish baseline (snapshots critical files for restoration)
python3 scripts/integrity.py baseline

# Check for modifications + injections
python3 scripts/integrity.py full

# AUTO-DETECT AND AUTO-RESPOND TO THREATS (recommended)
python3 scripts/integrity.py protect

# Quick health check
python3 scripts/integrity.py status

# Accept a legitimate change
python3 scripts/integrity.py accept SOUL.md

# Restore a tampered file from snapshot
python3 scripts/integrity.py restore SOUL.md

# Rollback a file to last git commit
python3 scripts/integrity.py rollback SOUL.md

# Quarantine a suspicious skill
python3 scripts/integrity.py quarantine bad-skill

# Restore a quarantined skill after investigation
python3 scripts/integrity.py unquarantine bad-skill
```

All commands accept `--workspace /path/to/workspace`. If omitted, auto-detects from `$OPENCLAW_WORKSPACE`, current directory, or `~/.openclaw/workspace`.

## Countermeasures

| Command | Action |
|---------|-...