ClawHub

AI Shield — OpenClaw Security Audit

Security checks across malware telemetry and agentic risk

Overview

This skill is a local OpenClaw configuration audit tool; it reads sensitive config data for an expected purpose and does not show artifact-backed exfiltration, persistence, or destructive behavior.

Install this only if you want a local audit of your OpenClaw configuration. Treat OpenClaw configs as sensitive because they may contain API keys, tokens, and remote access details; sanitize before sharing outputs or configs, and do not use any remote or premium audit flow unless its data handling is clearly explained.

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
88% confidence
Finding
The README advertises a premium remote audit via ACP but does not clearly disclose that configuration data may leave the local host for remote analysis. Because this skill handles security audits and likely processes sensitive OpenClaw configuration data, users could unknowingly transmit secrets, topology details, or tokens to an external service.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The workflow instructs reading `~/.openclaw/openclaw.json` and processing it with an audit tool, yet it gives no explicit privacy warning even though the same document acknowledges configs may contain API keys, tokens, and private keys. This increases the risk of exposing secrets in logs, summaries, copied outputs, or subsequent agent responses, especially because the skill encourages direct loading of a live config.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal