Doctor Check

Security checks across malware telemetry and agentic risk

Overview

This is a coherent system-diagnostic skill, but it can inspect sensitive local configuration, API-key validity, service state, and logs without clear scope or redaction rules.

Install only if you want an agent to perform local OpenClaw health checks. Before running it, specify which config files, services, and log paths may be inspected, require secrets and tokens to be redacted, and approve any file cleanup or credential validation 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 (1)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrase "检查问题" is broad and could match many ordinary troubleshooting requests, causing this diagnostic skill to activate when the user did not specifically intend to run it. Unintended invocation can leak system-health details, consume resources, or interfere with normal routing to a more appropriate skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal