ClawHub

OpenClaw Guide

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation helper that searches official OpenClaw sources and does not show hidden, destructive, or credential-stealing behavior.

Install this if you want OpenClaw answers grounded in official docs and source code. Be aware that it may use web searches/fetches, and its optional helper script may use your local GitHub CLI if an agent or user chooses to run it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (8)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
raise ValueError(f"Unknown search type: {search_type}")
    
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        return {"success": True, "output": result.stdout, "error": None}
    except subprocess.CalledProcessError as e:
        return {"success": False, "output": None, "error": e.stderr}
Confidence
70% confidence
Finding
result = subprocess.run(cmd, capture_output=True, text=True, check=True)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
"""
    cmd = ["gh", "api", f"repos/openclaw/openclaw/contents/{file_path}"]
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        data = json.loads(result.stdout)
        if "content" in data:
            import base64
Confidence
70% confidence
Finding
result = subprocess.run(cmd, capture_output=True, text=True, check=True)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition 'Any query related to OpenClaw that requires official documentation verification' is expansive and lacks clear boundaries or exclusion conditions. Because this is a markdown file, vague activation criteria apply here, and the wording does not specify what kinds of OpenClaw mentions should not invoke the skill.

Scope Creep

Low
Category
Excessive Agency
Content
### 3. Information Synthesis and Presentation
- Analyze gathered information from official sources
- Present clear, concise, and actionable guidance
- Avoid speculation or assumptions beyond documented facts
- Acknowledge when information is not available in official sources

### 4. Response Quality Standards
Confidence
70% confidence
Finding
beyond documented

Scope Creep

Low
Category
Excessive Agency
Content
### Verification Checklist
- [ ] Information sourced from official documentation or source code
- [ ] Links provided to original sources for user verification
- [ ] No speculation or assumptions beyond documented facts
- [ ] Response addresses the specific user question completely
- [ ] Technical accuracy verified against current implementation
Confidence
70% confidence
Finding
beyond documented

Unvalidated Output Injection

High
Category
Output Handling
Content
raise ValueError(f"Unknown search type: {search_type}")
    
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        return {"success": True, "output": result.stdout, "error": None}
    except subprocess.CalledProcessError as e:
        return {"success": False, "output": None, "error": e.stderr}
Confidence
95% confidence
Finding
subprocess.run(cmd, capture_output

Unvalidated Output Injection

High
Category
Output Handling
Content
"""
    cmd = ["gh", "api", f"repos/openclaw/openclaw/contents/{file_path}"]
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        data = json.loads(result.stdout)
        if "content" in data:
            import base64
Confidence
95% confidence
Finding
subprocess.run(cmd, capture_output

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal