ClawHub
Back to skill

Security audit

Test

Security checks across malware telemetry and agentic risk

Overview

This is a coherent monitoring skill, but it exposes sensitive operational data and supports host shell-command checks without enough access-control or safety guidance.

Review before installing. Run it only in a trusted local/admin environment, bind it to localhost or protect it with strong authentication and TLS, avoid exposing returned OpenClaw and system details publicly, disable command checks unless every config source is trusted, and run the service under a low-privilege account.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly advertises exposing runtime health, service connectivity, cron jobs, skills, dev servers, Docker status, and system metrics over HTTP, but the documentation does not discuss authentication, network binding restrictions, or redaction. Even if intended for monitoring, such an endpoint can disclose sensitive operational details that materially help attackers with reconnaissance and targeting.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill supports command-based health checks and process inspection, which means administrator-supplied commands will execute on the host. While this is configurable functionality rather than an immediate exploit by itself, the documentation understates the risk and provides no guardrails, making accidental unsafe command execution or abuse via untrusted configuration more likely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.