Skill flagged — suspicious patterns detected

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

Weekly Checker

v1.0.0

OpenClaw 每周例行检查 - 检查系统状态、安全风险、技能库健康,生成检查报告

0· 59·0 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 jirboy/weekly-checker.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Weekly Checker" (jirboy/weekly-checker) from ClawHub.
Skill page: https://clawhub.ai/jirboy/weekly-checker
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 weekly-checker

ClawHub CLI

Package manager switcher

npx clawhub@latest install weekly-checker
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description match the SKILL.md content: periodic checks of the gateway, skills library, Windows system, and security. However the skill references running a local script (tools/weekly_checker.py), reading skills/ and reports/ paths, and sending 飞书 notifications while the package declares no files, no required binaries, and no credentials. That gap means the implementation the SKILL.md expects is missing from the bundle.
!
Instruction Scope
SKILL.md instructs the agent to read system state, scan logs, check permissions, inspect the skills library, and notify via 飞书. These are broad file/system access operations and outbound notifications. The instructions also reference executing a local Python tool (python tools/weekly_checker.py) that is not included. The instructions grant broad discretion (automatic scheduling, scanning many paths) without specifying safe boundaries or required approvals.
Install Mechanism
No install spec and no code files are included — this minimizes the risk of the skill dropping code onto disk. However, the SKILL.md expects a tools/weekly_checker.py and scheduled task behavior that are not present; the lack of an install mechanism means those actions would rely on pre-existing host-side artifacts or external setup.
!
Credentials
The instructions require sending 飞书 (Feishu) notifications but the skill declares no environment variables, webhooks, or credentials. It also says it will inspect skill repository files and system logs but declares no config paths or permissions. The absence of declared credentials/paths is inconsistent with the actions described and could hide required secrets or setup steps.
Persistence & Privilege
The skill is not marked always:true and is user-invocable; autonomous invocation is allowed (disable-model-invocation:false). SKILL.md mentions automatic weekly execution and scheduling, but no mechanism to install or enable a scheduler is provided. This is not itself malicious but is a missing detail the user should verify.
What to consider before installing
Do not install or enable this skill until you verify a few things: (1) Ask the publisher for the implementation (tools/weekly_checker.py and any other scripts) and review that code — the SKILL.md references that script but it is not bundled. (2) Confirm how 飞书 notifications are configured (webhook or token) and never provide credentials without reviewing how they are used; the skill metadata declares no env vars for notifications. (3) Decide which filesystem paths the skill is allowed to read (logs, skills/, reports/) and restrict access or run the skill in a sandbox. (4) If you plan to enable automatic scheduling, require an explicit installation step that you can inspect (cron/task creation). (5) If you cannot get the source code or clear configuration for notifications and scheduling, treat this skill as untrusted and avoid granting it system-level access.

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

latestvk9754w2dfpk9yvasmt12ar3skh84zr34
59downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

OpenClaw 每周例行检查

版本: 1.0
创建: 2026-03-10
作者: SuperMike


功能说明

每周自动执行系统全面检查,包括:

  1. OpenClaw 网关 - 运行状态、版本检查
  2. 技能库健康 - 文档完整性、技能数量
  3. 配置安全 - 凭据管理、访问控制
  4. Windows 系统 - CPU、内存、磁盘、网络
  5. 安全风险 - 敏感信息、文件权限
  6. 日志检查 - 日志大小、异常记录

触发语句:

  • "执行每周检查"
  • "检查系统安全"
  • "生成周检报告"

检查频率

自动执行

  • 时间: 每周一 09:00
  • 方式: 定时任务自动运行
  • 通知: 发现问题立即飞书通知

手动执行

  • 对话触发:"执行每周检查"
  • 命令行:python tools/weekly_checker.py

检查清单

OpenClaw 系统

  • 网关运行状态
  • 版本号检查
  • 配置文件安全性
  • 技能库文档完整性
  • 日志文件大小

Windows 系统

  • CPU 使用率(阈值:90%)
  • 内存使用率(阈值:90%)
  • 磁盘空间(阈值:90%)
  • 网络连接状态

安全检查

  • 敏感文件权限
  • 明文密钥检测
  • 工作目录完整性
  • 技能库异常检测

通知策略

🔴 严重问题(立即通知)

  • 网关未运行
  • CPU/内存/磁盘 >95%
  • 发现明文密钥泄露
  • 技能库异常

🟡 警告信息(汇总通知)

  • CPU/内存/磁盘 >90%
  • 技能缺少文档
  • 日志文件过大
  • 配置建议

✅ 正常状态

  • 记录日志
  • 不主动通知

报告格式

JSON 报告

位置: reports/weekly_check_YYYYMMDD.json

内容:

{
  "check_time": "2026-03-10T09:00:00",
  "openclaw_gateway": {...},
  "openclaw_version": {...},
  "configuration": {...},
  "skills": {...},
  "windows_system": {...},
  "security": {...},
  "issues": [...],
  "warnings": [...]
}

飞书通知

格式:

🔴 OpenClaw 每周检查 - 发现问题

检查时间:2026-03-10 09:00

发现 2 个问题:
• [网关] 网关未运行
  建议:运行 openclaw gateway start
• [磁盘] C 盘空间不足:92%
  建议:清理磁盘空间

系统状态摘要:
- OpenClaw 网关:error
- 技能库:45/46 有文档
- CPU: 5%
- 内存:45%
- 安全风险:0 个

处理流程

发现问题

  1. 记录问题详情
  2. 评估严重程度
  3. 生成修复建议
  4. 飞书通知纪老师
  5. 等待指示(不擅自修改)

确保万无一失的情况

仅在以下情况可自动修复:

  • ✅ 有明确修复方案
  • ✅ 修复操作可逆
  • ✅ 风险为零
  • ✅ 已有成功先例

示例:

  • ✅ 清理>30 天的旧日志文件
  • ✅ 重启已停止的网关服务
  • ❌ 修改系统配置
  • ❌ 删除技能文件
  • ❌ 修改权限设置

相关文件

  • 检查工具:tools/weekly_checker.py
  • 技能文档:skills/weekly-checker/SKILL.md
  • 检查报告:reports/weekly_check_*.json
  • 通知模板:reports/feishu_notification_*.txt

历史报告

查看历史:

# 查看最近 5 次报告
Get-ChildItem reports/weekly_check_*.json | Select-Object -Last 5

趋势分析:

  • 网关稳定性
  • 技能库增长
  • 系统资源使用趋势
  • 安全问题统计

最佳实践

检查前

  • 确保网关运行
  • 确保网络连接
  • 确保有足够权限

检查后

  • 审查检查报告
  • 处理严重问题
  • 跟踪警告信息
  • 归档历史报告

问题处理

  • 优先处理严重问题
  • 记录处理过程
  • 验证修复效果
  • 更新检查清单

本技能用于定期系统检查,发现问题及时通知,谨慎执行修复操作。

Comments

Loading comments...