Security Scanner PlusSAFE

🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: Security Scanner
description: >
  Scan AI agent skills for security vulnerabilities, dangerous code patterns,
  and undeclared permissions. Three-layer analysis: dependency CVE scanning,
  static code analysis, and permission auditing. Returns structured JSON risk 
  report. Use when the user asks to scan a skill for security issues, check 
  for vulnerabilities, audit permissions, or assess skill safety.
metadata:
  requires:
    env:
      - CLAW0X_API_KEY
---

# Security Scanner

**Free skill by [Claw0x](https://claw0x.com)** — powered by Claw0x Gateway API.

Scan AI agent skills for security vulnerabilities across three layers: dependency CVEs, dangerous code patterns, and undeclared permissions. Returns a structured JSON risk report with an overall score (0–100).

> **Free to use.** This skill costs nothing. Just [sign up at claw0x.com](https://claw0x.com), create an API key, and start calling. No credit card, no wallet top-up required.

## Quick Reference

| When This Happens | Scan For | What You Get |
|-------------------|----------|--------------|
| Installing third-party skill | All vulnerabilities | Risk score + CVE list |
| Before publishing skill | Code patterns + permissions | Security audit report |
| Dependency update | New CVEs | Updated vulnerability list |
| User reports suspicious behavior | Undeclared permissions | Permission audit |
| CI/CD pipeline | Automated security check | Pass/fail + recommendations |
| Skill marketplace review | Trust score calculation | Approval decision data |

**Why API-based?** Centralized CVE database (OSV.dev), consistent scanning rules, no local setup required.

---

## 5-Minute Quickstart

### Step 1: Get API Key (30 seconds)
Sign up at [claw0x.com](https://claw0x.com) → Dashboard → Create API Key

### Step 2: Scan Your First Skill (1 minute)
```bash
curl -X POST https://api.claw0x.com/v1/call \
  -H "Authorization: Bearer ck_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "skill": "security-scanner",
    "input": {
      "repo_url": "https://github.com/owner/repo"
    }
  }'
```

### Step 3: Review Risk Report (instant)
```json
{
  "overall_risk": "medium",
  "risk_score": 35,
  "dependency_scan": {
    "vulnerabilities": [
      {
        "id": "GHSA-jf85-cpcp-j695",
        "severity": "high",
        "package_name": "lodash",
        "summary": "Prototype Pollution"
      }
    ]
  },
  "code_scan": {
    "findings": [
      {
        "rule_id": "SHELL_INJECT",
        "severity": "critical",
        "file": "handler.ts",
        "line": 42
      }
    ]
  },
  "recommendations": [
    "Critical: Shell injection pattern detected",
    "High: [email protected] has known vulnerabilities"
  ]
}
```

### Step 4: Fix Issues (2 minutes)
```bash
# Update vulnerable dependency
npm update lodash

# Fix shell injection
# Replace: exec(userInput)
# With: execFile('command', [userInput])
```

**Done.** Your skill is now more secure.

---

## Real-World Use Cases

### Scenario 1: Skill Marketplace Vetting
**Problem**: You run a skill marketplace and need to vet submissions before approval

**Solution**:
1. Seller submits skill via GitHub URL
2. Automated scan runs on submission
3. Risk score determines approval workflow
4. High-risk skills get manual review
5. Low-risk skills auto-approve

**Example**:
```typescript
async function reviewSkillSubmission(repoUrl) {
  const response = await fetch('https://api.claw0x.com/v1/call', {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${process.env.CLAW0X_API_KEY}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      skill: 'security-scanner',
      input: { repo_url: repoUrl }
    })
  });
  
  const scan = await response.json();
  
  if (scan.risk_score > 50) {
    await queue.add('manual-review', { repoUrl, scan });
  } else if (scan.risk_score < 20) {
    await approveSkill(repoUrl);
  } else {
    await requestSellerFixes(repoUrl, scan.recommendations);
  }
}
// Result: 80% of submissions auto-processed, 95% fewer security incidents
```

### Scenario 2: CI/CD Security Gate
**Problem**: Developers push code with vulnerabilities that reach production

**Solution**:
1. Add security scan to CI/CD pipeline
2. Block merges if risk score > threshold
3. Require fixes before deployment
4. Track security metrics over time

**Example**:
```yaml
# .github/workflows/security.yml
- name: Security Scan
  run: |
    RESULT=$(curl -X POST https://api.claw0x.com/v1/call \
      -H "Authorization: Bearer $CLAW0X_API_KEY" \
      -d '{"skill":"security-scanner","input":{"repo_url":"${{ github.repository }}"}}')
    
    RISK_SCORE=$(echo $RESULT | jq -r '.risk_score')
    
    if [ $RISK_SCORE -gt 50 ]; then
      echo "Security scan failed: risk score $RISK_SCORE"
      exit 1
    fi
# Result: 90% reduction in production security issues
```

### Scenario 3: Dependency Monitoring
**Problem**: Your skills use dependencies that get new CVEs over time

**Solution**:
1. Schedule weekly scans of all published skills
2. Alert when new vulnerabilities appear
3. Auto-create PRs with dependency updates
4. Track remediation time

**Example**:
```javascript
// Cron job: every Monday
async function weeklySecurityAudit() {
  const skills = await db.skills.findMany({ status: 'published' });
  
  for (const skill of skills) {
    const response = await fetch('https://api.claw0x.com/v1/call', {
      method: 'POST',
      headers: {
        'Authorization': `Bearer ${process.env.CLAW0X_API_KEY}`,
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({
        skill: 'security-scanner',
        input: { repo_url: skill.repo_url }
      })
    });
    
    const scan = await response.json();
    
    // Check if risk increased
    if (scan.risk_score > skill.last_risk_score) {
      await notifyMaintainer(skill, scan);
      await createUpdatePR(skill, scan.recommendations);
    }
    
    await db.skills.update({
      where: { id: skill.id

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

declared (1 observation(s))

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

<key>k5Ey9KFlkqpj+SDkUw+5ED9lTA3En/qUi0zdrydUCH3kMWTE3Eh65NXnFCaxlY2omY2JHnlEoK7Li7oOEvM7eG5VPdcO/sFlMfoCRdnLYdepJ+uLzYwOWR8W4yQVve/clxVFTVRL4DFleKInGdpAxIbHZT2yi4ADAMENls1N1XSLojRuqXePXDeAT/4Mv4TTx0s

Gates applied: no_behavioural_pass.