ClawHub

OpenClaw Doctor

Security checks across malware telemetry and agentic risk

Overview

This is a read-only OpenClaw health-check skill that inspects expected system status and configuration information and tells the agent to redact secrets.

Install this only if you are comfortable letting an agent inspect OpenClaw configuration, model/API-key status, cron status, installed skills, and memory/workspace file status. Prefer invoking it explicitly for OpenClaw diagnostics, and authorize any repairs or configuration changes separately.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manual trigger phrase '检查系统状态' is very broad and overlaps with ordinary support or status questions, making accidental activation likely. In the context of a diagnostic skill with access to system health details, this broad trigger increases the chance of invoking privileged inspection behavior when a user merely asks for general status information.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manual trigger phrase '检查系统状态' is very broad and overlaps with ordinary support or status questions, making accidental activation likely. In the context of a diagnostic skill with access to system health details, this broad trigger increases the chance of invoking privileged inspection behavior when a user merely asks for general status information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal