Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Temp Notification Reader

v1.0.0

读取 macOS 通知中心,导出到 memory/computer_io/notification/ 目录。让 OpenClaw 了解你的工作动态。

0· 89·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for gift-is-coding/temp-notification-reader.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Temp Notification Reader" (gift-is-coding/temp-notification-reader) from ClawHub.
Skill page: https://clawhub.ai/gift-is-coding/temp-notification-reader
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install temp-notification-reader

ClawHub CLI

Package manager switcher

npx clawhub@latest install temp-notification-reader
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (read macOS notifications, export to OpenClaw memory) align with the code and scripts, which locate the local notification DB, copy it, parse notifications, and write markdown summaries into the OpenClaw memory directory. No unrelated credentials, cloud APIs, or unexpected binaries are requested.
Instruction Scope
Runtime instructions and scripts explicitly tell the user to run the included export and summary scripts, schedule them (cron/OpenClaw), and grant macOS permissions. They also instruct adding Full Disk Access for python3 so the script can read the notification DB — this is required for the task but grants python3 broad disk access (sensitive). The README/INSTALL text suggests optional npm publishing/commands, but the shipped package is instruction-and-script based; that is a minor documentation mismatch, not a functional inconsistency.
Install Mechanism
There is no automated install spec in the registry (instruction-only). The SKILL.md and README propose cloning the GitHub repo or an npm global install path; the provided files are local scripts and Python code, and the code contains no network calls. No archive downloads or remote installers are invoked by the skill itself.
Credentials
The skill asks for no external credentials or environment secrets. It does rely on environment variables for configuration (OUTPUT_DIR, NOTIF_LOOKBACK_MINUTES, WORK_LOOKBACK_MINUTES, MEMORY_DIR) which are reasonable. However, it requires the user to grant system-level permissions (notification access and Full Disk Access for python3) to function; these permissions are proportionate to reading the notification DB but are sensitive and should be granted only if you trust the code.
Persistence & Privilege
The skill is not marked always:true and does not modify other skills or system-wide agent settings automatically. It writes output into OpenClaw's memory directory and uses /tmp for temporary DB copies—both expected. Scheduling is user-directed (cron or OpenClaw jobs) rather than forced.
Assessment
This skill appears to do what it says: read your local macOS notification database and write local summaries for OpenClaw. Key things to consider before installing: - Privacy: the tool reads notification titles and bodies (potentially sensitive). Review the included Python and shell scripts yourself to confirm you are comfortable with what will be collected and where it is stored (~/.openclaw/workspace/memory by default). - macOS permissions: to access the notification DB you'll likely need to grant notification access and Full Disk Access to python3 (a broad privilege). Only grant these if you trust the code and its source. - Source verification: SKILL.md and README reference a GitHub repo (https://github.com/gift-is-coding/...), but the registry metadata shows unknown source/homepage. Confirm the repository origin and review commit history before cloning or running scripts. - Cron / scheduling: adding a recurring job will repeatedly collect notifications. Test the export scripts manually first to inspect outputs, then add scheduling if desired. - Running safely: run the scripts manually in a controlled environment (not as root), consider using a dedicated Python virtualenv, and inspect the files created in /tmp and the OpenClaw memory directory. Avoid a global npm install unless you verify the published package. If you want lower-risk testing, run read_notifications_visual.py or read_notifications.py with a short lookback and output to a local temp file to inspect results before enabling persistent scheduling or granting broad OS permissions.

Like a lobster shell, security has layers — review code before you run it.

latestvk97cw3zkqsb0wabaygfyvay53h8556v1
89downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

macOS Notification Reader

让 OpenClaw 读取你的 macOS 通知,自动生成每日工作摘要

Read your macOS notifications and generate daily work summaries for OpenClaw

这是一个为 OpenClaw 打造的技能(Skill),可以读取 macOS 通知中心的内容,帮助 AI 助手更好地了解你的工作动态。


🎯 这是什么? / What is this?

这个工具会把你的 macOS 通知导出到 OpenClaw 的 memory 目录,让 OpenClaw 能够:

  • 📬 知道谁在找你(Teams、Outlook、WeChat...)
  • 📅 了解你的日程提醒
  • ✅ 提取待办事项(会议、审批、deadline...)
  • 🧠 记住你最近在忙什么

📁 输出文件结构 / Output File Structure

memory/YYYY-MM-DD/
└── computer_io/
    └── notification/
        ├── YYYYMMDD-HHMMSS.md          # 原始通知导出
        └── work-summary-YYYYMMDD-HHMMSS.md  # 工作摘要(推荐)

🚀 安装 / Installation

前置要求

  • macOS 系统
  • Python 3.8+ (python3 --version 检查)
  • OpenClaw 已安装并运行

步骤 1:放入 OpenClaw Skills 目录

# 克隆项目
git clone https://github.com/gift-is-coding/macos-notification-reader.git

# 复制到 OpenClaw skills 目录
cp -r macos-notification-reader ~/.openclaw/workspace/skills/

# 给脚本执行权限
chmod +x ~/.openclaw/workspace/skills/macos-notification-reader/scripts/*.sh

步骤 2:首次运行授权

~/.openclaw/workspace/skills/macos-notification-reader/scripts/export-notification.sh

首次运行时,macOS 会弹窗请求「通知访问权限」,点击允许


⚙️ 配置定时任务 / Configure Cron Job

方法一:通过 OpenClaw 配置(推荐)

编辑 ~/.openclaw/cron/jobs.json,添加:

{
  "name": "Notification Reader",
  "schedule": "*/30 * * * *",
  "command": "~/.openclaw/workspace/skills/macos-notification-reader/scripts/export-notification.sh",
  "timezone": "Asia/Shanghai"
}

这会让 OpenClaw 每 30 分钟自动抓取一次通知。

方法二:手动添加 crontab

crontab -e

添加:

*/30 * * * * ~/.openclaw/workspace/skills/macos-notification-reader/scripts/export-notification.sh >> ~/.openclaw/logs/notification.log 2>&1

💼 使用方式 / Usage

导出所有通知

~/.openclaw/workspace/skills/macos-notification-reader/scripts/export-notification.sh

工作摘要模式(推荐)

只提取工作相关通知(Teams/Outlook/WeChat):

~/.openclaw/workspace/skills/macos-notification-reader/scripts/work-summary.sh

自定义时间范围

# 只看过去 1 小时的通知
NOTIF_LOOKBACK_MINUTES=60 ~/.openclaw/workspace/skills/macos-notification-reader/scripts/export-notification.sh

# 工作摘要只看过去 2 小时
WORK_LOOKBACK_MINUTES=120 ~/.openclaw/workspace/skills/macos-notification-reader/scripts/work-summary.sh

🔐 隐私 / Privacy

  • ✅ 数据保存在本地(OpenClaw memory 目录),不上传任何服务器
  • ✅ 只读取通知标题和内容,不读取附件
  • ✅ 支持一键清理:rm -rf ~/.openclaw/workspace/memory/*/computer_io/notification/

🛠️ 故障排查 / Troubleshooting

显示 0 条通知?

  1. 检查权限是否授权:

    # 打开系统设置 / System Settings
    open "x-apple.systempreferences:com.apple.preference.security?Privacy_Notifications"
    
  2. 快速调试:

    python3 ~/.openclaw/workspace/skills/macos-notification-reader/scripts/read_notifications.py --minutes 5 --output /tmp/debug.txt
    cat /tmp/debug.txt
    

权限被拒绝?

chmod +x ~/.openclaw/workspace/skills/macos-notification-reader/scripts/*.sh

📞 支持 / Support


Made with ❤️ for OpenClaw

Comments

Loading comments...