ClawHub
Back to skill

Security audit

System Resource Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill only runs a disclosed local script to print basic system health metrics and shows no evidence of data theft, persistence, or system modification.

Install this only if you are comfortable with the agent running the included local shell script to read and display basic host health metrics. The reviewed version does not show network transmission, credential access, persistence, or system-changing behavior.

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
94% confidence
Finding
The listed triggers "system status," "resource usage," and especially "server health" are generic phrases that could appear in ordinary conversation about infrastructure, making unintended invocation more likely. The file does not provide narrower scope, explicit constraints, or negative examples to clarify when this skill should versus should not activate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.