360Guard

What this skill does

# 360Guard 🛡️

> 360-degree comprehensive security review — Like antivirus for your Skills

## 1. When to Use

- Before installing any Skill from ClawHub
- Before installing any Skill from GitHub or other sources
- When evaluating code shared by other Agents
- Any time you're asked to install unknown code
- Periodic audit of installed Skills (recommended monthly)
- Before running high-risk Skills for second verification

## 2. Core Principles

```
┌─────────────────────────────────────────────────────────────┐
│  🛑 Security Layer Priority                                 │
├─────────────────────────────────────────────────────────────┤
│  ⛔ EXTREME → Absolutely refuse to install                  │
│  🔴 HIGH    → Requires human approval                       │
│  🟡 MEDIUM  → Full code review + limited permissions        │
│  🟢 LOW     → Basic review OK                               │
└─────────────────────────────────────────────────────────────┘
```

## 3. Security Checklist

### 3.1 Base Red Flags (from Skill Vetter)

```
🚨 Reject immediately if you see:
────────────────────────────────────────────────────────────
• curl/wget to unknown URLs
• Sends data to external servers
• Requests credentials/tokens/API keys
• Reads ~/.ssh, ~/.aws, ~/.config without clear reason
• Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• Uses base64 decode on anything
• Uses eval() or exec() with external input
• Modifies system files outside workspace
• Installs packages without listing them
• Network calls to IPs instead of domains
• Obfuscated code (compressed, encoded, minified)
• Requests elevated/sudo permissions
• Accesses browser cookies/sessions
• Touches credential files
────────────────────────────────────────────────────────────
```

### 3.2 Extended Red Flags (New)

#### 3.2.1 Persistence & Auto-start

```
🔴 Persistence check:
• Creates cron job / systemd service
• Modifies ~/.ssh/authorized_keys
• Writes to /etc/hosts
• Adds Login Items / Startup Items
• Modifies .bashrc / .zshrc / profile
• Registers LaunchAgent (macOS)
• Installs systemd user service
```

#### 3.2.2 Monitoring & Eavesdropping

```
🔴 Monitoring permissions check:
• Requests screen capture/recording (screencapture)
• Requests audio recording permission
• Keyloggers
• Accesses microphone/camera
• File system monitoring (fswatch/inotify)
```

#### 3.2.3 Data & Privacy

```
🔴 Data theft check:
• Reads clipboard (pbpaste)
• Reads environment variables (especially API_, SECRET, TOKEN)
• Accesses browser history/bookmarks
• Accesses macOS Keychain
• Accesses iMessage/SMS
• Accesses contacts/calendar
• Accesses photo library
```

#### 3.2.4 Network & Communication

```
🔴 Network anomaly check:
• Initiates reverse shell (nc -e / bash -i)
• Uses Tor proxy
• DNS queries to suspicious domains
• WebSocket long connections
• IRC connections
• Non-standard ports (>65535 or <1024 unusual)
• Hardcoded IP addresses (non-local)
```

#### 3.2.5 Code Execution (Advanced)

```
🔴 Dynamic execution check:
• Dynamic import (importlib.import_module)
• __import__() dynamic loading
• compile() dynamic compilation
• xmlrpc / jsonrpc remote calls
• pickle / yaml / marshal deserialization
• exec() / eval() any string
• subprocess shell=True
```

#### 3.2.6 File System

```
🟡 File operation check:
• Writes to executable paths outside /tmp
• Modifies /usr/local/bin
• Writes .dmg/.pkg installers
• Creates .hidden files/directories
• File permission modification (chmod +x)
• Symbolic links (pointing external)
• Contains binary files (.so/.dylib/.exe/.bin)
```

#### 3.2.7 Dependencies & Supply Chain

```
🟡 Supply chain check:
• Dependency version range too wide (>1.0.0 not ^1.0.0)
• Dependencies from private/unknown sources
• Dependencies on deprecated packages
• Silent additional dependency downloads
• References other unvetted Skills
• Uses git submodule (may point to malicious repo)
```

#### 3.2.8 Social Engineering

```
🟡 Social engineering check:
• Mimics popular Skill names (e.g., "github", "weather-ai")
• README overpromises ("one-click to do everything...")
• No source code, only compiled binaries
• Author has no history
• Downloads vs stars ratio suspicious (fake reviews)
```

---

## 4. Risk Classification

| Risk Level | Example Checks | Action |
|------------|----------------|--------|
| 🟢 LOW | Text processing, weather, note formatting | Basic review, OK to install |
| 🟡 MEDIUM | File I/O, browser control, API calls | Full review + limited permissions |
| 🔴 HIGH | Credential access, Keychain, network requests | Human approval + sandbox test |
| ⛔ EXTREME | Persistence, root access, keylogging, reverse shell | **Refuse** |

---

## 5. Trust Hierarchy

| Source | Review Level | Recommendation |
|--------|--------------|----------------|
| Official OpenClaw Skills | Low (still review) | Basic check |
| High-star Repo (1000+) | Medium | Standard check |
| Known Authors | Medium | Standard check |
| Unknown Sources | High | Full check |
| Requests credentials | Extreme | **Refuse** |
| Modifies system files | Extreme | **Refuse** |

---

## 6. Automated Scanning Scripts

### 6.1 Quick Scan (quick-scan.sh)

```bash
#!/bin/bash
# Usage: ./quick-scan.sh /path/to/skill
# Output: Quick risk assessment report

SKILL_PATH=$1
echo "🔍 360Guard Quick Scan: $SKILL_PATH"
echo "================================"

# Check dangerous functions
echo -e "\n📡 Network request check:"
grep -r "curl\|wget\|fetch\|http\.\|https\.\|socket" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py" | head -5

# Check sensitive file access
echo -e "\n🔑 Sensitive path check:"
grep -r "~/.ssh\|~/.aws\|~/.config\|/etc/hosts\|authorized_keys" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py"

# Check dangerous commands
echo -e "\n⚠️ Dangerous command check:"
grep -r "eval\|exec\|shell=True\|base64 -d\|openssl" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py"

echo -e "\n✅ Quick scan complete"
```

### 6.2 Full Scan (full-scan.sh)

```bash
#!/bin/bash
# Usage: ./full-scan.sh /path/to/skill
# Output: Complete security assessment report

SKILL_PATH=$1
REPORT="$SKILL_PATH/360guard-report.txt"

echo "🛡️ 360Guard Full Scan: $SKILL_PATH" | tee "$REPORT"
echo "========================================" | tee -a "$REPORT"

# 1. File structure check
echo -e "\n📁 File structure:" | tee -a "$REPORT"
find "$SKILL_PATH" -type f | head -20 | tee -a "$REPORT"

# 2. Dangerous function scan
echo -e "\n⚠️ Dangerous function scan:" | tee -a "$REPORT"
for pattern in "eval(" "exec(" "shell=True" "base64" "subprocess" "importlib" "__import__" "pickle" "yaml.load" "xmlrpc" "socket.create_connection"; do
  result=$(grep -r "$pattern" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py" 2>/dev/null)
  if [ -n "$result" ]; then
    echo "  ❌ Found: $pattern" | tee -a "$REPORT"
    echo "$result" | head -3 | tee -a "$REPORT"
  fi
done

# 3. Sensitive path scan
echo -e "\n🔑 Sensitive path scan:" | tee -a "$REPORT"
for pattern in "~/.ssh" "~/.aws" "~/.config" "/etc/hosts" "authorized_keys" "keychain" "credentials" ".env"; do
  result=$(grep -r "$pattern" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py" 2>/dev/null)
  if [ -n "$result" ]; then
    echo "  ⚠️ Warning: $pattern" | tee -a "$REPORT"
  fi
done

# 4. Network request scan
echo -e "\n🌐 Network request scan:" | tee -a "$REPORT"
grep -r "http://\|https://\|wget\|curl\|fetch" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py" | grep -v "^#" | head -10 | tee -a "$REPORT"

# 5. Persistence check
echo -e "\n⏰ Persistence check:" | tee -a "$REPORT"
for pattern in "cron" "systemd" "launchd" "login item" "startup" "autostart"; do
  result=$(grep -ri "$pattern" "$SKILL_PATH" --include="*.sh" --include="*.js" --include="*.py" 2>/dev/null)
  if [ -n "$result" ]; then
    echo "  🔴 High risk: $pattern" | tee -a "$REPORT"
  fi
done

# 6. Dependency check
echo -e "\n📦 Dependency check:" | tee -a "$REPORT"
if [ -f "$SKILL_PATH