OpenClaw Doctor

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed system diagnostic skill; its main risk is that broad auto-trigger wording could expose local status details when invoked too casually.

Install if you want an OpenClaw diagnostic helper, but invoke it deliberately and avoid sharing its output publicly because it may include local versions, configuration status, cron details, or memory-system metadata.

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 (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The README states the AI will automatically invoke the skill 'when needed' and also provides a very broad trigger phrase ('检查系统状态'). This can cause unintended activation in loosely related conversations, leading to unnecessary system inspection and disclosure of environment details such as versions, configuration status, cron state, and memory artifacts. In a diagnostic skill, broad auto-triggering increases risk because the skill touches sensitive operational metadata even if it does not itself appear overtly malicious.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal