Back to skill

Security audit

Windows System Monitor

Security checks for vulnerabilities and agentic risk

Overview

This Windows monitoring skill is coherent and disclosed, but users should configure any Feishu alerting carefully because it may send system-status details outside the machine.

Install only if you want a Windows system-health helper. Before enabling Feishu alerts or recurring checks, confirm the recipient, webhook or app configuration, and exactly what host, process, network, and log details will be included in notifications.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are generic system-health requests such as '检查系统状态' and 'Windows 运行正常吗', which can overlap with ordinary conversational help or broad diagnostic intents. Because the skill is user-invocable and can initiate monitoring/reporting behavior, overly broad activation increases the chance of unintended execution and accidental disclosure of system status or follow-on notifications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises immediate Feishu notifications for serious system conditions but does not describe what data may be transmitted, who receives it, or any consent/privacy controls. In a system-monitoring context, alerts can contain sensitive host information, resource usage, process names, or operational details that could leak internal environment data to external messaging systems.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.

md
- 监控工具:`tools/windows_system_monitor.py`
- 检查报告:`reports/windows_system_check.json`
- 技能文档:`skills/windows-system-monitor/SKILL.md`

---