ClawHub
Back to skill

Security audit

Claw Security Self Check

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only OpenClaw security audit helper that generates local reports without remediation or hidden persistence.

Install only on an OpenClaw host you are authorized to audit. The generated reports are sanitized but may still reveal ports, policies, file permissions, and other internal security posture, so treat them as internal security material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/host-baseline.mjs:151

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/host-baseline.mjs:56