ClawHub
Back to skill

Security audit

服务器监控

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Linux server-monitoring skill with disclosed read-only status commands, plus optional scheduling and alerts that users should enable deliberately.

Install this only where local server-status inspection is appropriate. Treat the output as infrastructure-sensitive, and review any cron, HEARTBEAT.md, or notification setup before enabling it so hostnames, process names, and resource metrics are not sent or repeated unexpectedly.

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
89% confidence
Finding
The trigger phrases are broad enough to match common user requests like checking how a system is doing, which can cause the skill to activate in contexts where the user did not explicitly consent to server inspection. Because the skill runs shell-based monitoring commands and reveals host/resource details, unintended activation can expose sensitive operational information or cause unnecessary command execution.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The proactive alerting language allows the skill to act on 'resource over threshold' conditions without clear opt-in, policy boundaries, or target constraints. In an agent environment, this can lead to unsolicited monitoring, repeated execution, or notification behavior that the user or system owner did not authorize, increasing the chance of data leakage and operational misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.