任务守望者与弹窗杀手 (Task Watchdog)

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill has no hidden code, but it asks the agent to run unattended and click away system pop-ups, which could close important warnings or affect the computer without the user present.

Review this skill carefully before use. It is best used only after you define the exact task window, allowed pop-up types, safe buttons to click, maximum runtime, and alert destination. Do not let it automatically dismiss system, security, restart, update, deletion, or payment dialogs unless you are certain those actions are safe.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent could accidentally close or ignore an important warning, update prompt, error dialog, or security alert while the user is away.

Why it was flagged

This grants the agent unattended authority to click UI controls and dismiss dialogs, but the skill does not define a strict allowlist or require user confirmation for potentially important system/security prompts.

Skill content
如果发现无关弹窗,立即识别其右上角的“X”按钮,或“稍后提醒”、“关闭”、“忽略”等按钮,模拟鼠标点击将其关闭。
Recommendation

Use only with a tightly defined target window and approved dialog/button list; require confirmation or alert-only behavior for system, security, update, restart, payment, deletion, or error dialogs.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The agent may keep monitoring and interacting with the desktop until the task completes or is stopped.

Why it was flagged

The skill explicitly describes a long-running autonomous loop. This is disclosed and purpose-aligned, but users should notice that it continues acting while they are away.

Skill content
进入休眠状态。每隔 5 分钟醒来一次,执行以下检查
Recommendation

Set an explicit stop condition, maximum runtime, and manual cancel method before starting the watchdog mode.

What this means

A failure alert could reveal private information visible on the screen or send status details to a webhook destination.

Why it was flagged

The skill may capture the full screen and use a user-configured webhook for alerts. The artifact does not clearly state whether screenshots are sent, but screenshots and webhook notifications can expose sensitive screen content if configured broadly.

Skill content
立即对当前屏幕进行完整截图。调用系统或用户预设的通知机制(如果用户配置了 Webhook 报警)
Recommendation

Use a trusted webhook destination, avoid displaying sensitive information during monitoring, and clarify whether screenshots are stored or transmitted.