Task Scheduler

Security checks across malware telemetry and agentic risk

Overview

This scheduler is not malicious, but it deserves review because it can create persistent tasks that read local files, write logs, retry automatically, and send reports to Feishu without clearly bounded controls.

Install only if you are comfortable granting the agent scheduling authority. Before enabling tasks, require explicit confirmation for create, modify, delete, and external-send actions; define exact task names, schedules, end dates, allowed files, Feishu recipients, and log retention.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The trigger list includes broad terms such as '自动化' and '提醒', which are common in ordinary conversation and can cause accidental activation of the skill. In a scheduling skill, unintended activation is risky because it can create persistent tasks or reminders without the user clearly intending to invoke this capability.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill advertises deletion and external notification features, including Feishu delivery, but does not clearly warn users that actions may remove tasks or send content to external systems. This creates a real risk of unintended destructive changes or data exfiltration, especially because scheduled jobs may read local files and transmit generated reports automatically.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal