ClawHub
Back to skill

Security audit

minutes-task

Security checks across malware telemetry and agentic risk

Overview

The skill is purpose-aligned for Windows minute-level scheduling, but it gives the agent persistent Task Scheduler authority without enough explicit user control.

Review this skill before installing. It is not evidence of malware, but it can create background Windows tasks that keep running after the agent session. Only use it when you want a persistent local scheduled task, and have the agent show the task name, script path, command, trigger interval, and any delete or overwrite action before applying changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The skill explicitly instructs the agent to create persistent Windows Scheduled Tasks and associated scripts that will continue executing outside the agent runtime. That is a real security-sensitive capability because it establishes durable execution on the host and can be repurposed for unintended automation or persistence if the task content is unsafe or user intent is misunderstood.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill says the agent should complete the workflow automatically and includes creation, modification, disabling, enabling, and deletion of scheduled tasks without an explicit warning about system changes. This is dangerous because it can alter persistent system state and background execution behavior without clear informed consent, increasing the risk of surprise persistence, misconfiguration, or abuse.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrase "每 N 分钟定时执行" is broad enough to match many generic scheduling requests and could cause this skill to be selected outside its intended narrow use case. In this skill’s context, that increases the chance of routing users into a Windows Task Scheduler workflow that bypasses the platform’s built-in scheduler limitations, which can lead to unintended persistence or execution behavior on Windows hosts.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.