Skill flagged — suspicious patterns detected

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

Workspace Auto Maintenance

v1.0.0

Automates OpenClaw workspace health checks and fixes issues like redundant files, permissions, naming, and Git commits across platforms.

0· 77·0 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 zhangyi881/workspace-auto-maintenance.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Workspace Auto Maintenance" (zhangyi881/workspace-auto-maintenance) from ClawHub.
Skill page: https://clawhub.ai/zhangyi881/workspace-auto-maintenance
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 workspace-auto-maintenance

ClawHub CLI

Package manager switcher

npx clawhub@latest install workspace-auto-maintenance
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description align with the code: the script scans the workspace, renames/moves files, adjusts script permissions, and auto-commits Git changes — all consistent with an 'auto maintenance' tool.
!
Instruction Scope
SKILL.md instructs the user to run the Python script (and to use --fix to auto-repair). The code will move non-essential root files into a tmp folder, rename memory files, change ACLs on .ps1 files, and run git add/commit. These are local, modifying operations that can change or hide user data and create commits without interactive confirmation; the README does not adequately warn about risk or require an explicit confirmation/dry-run before performing destructive actions.
Install Mechanism
No install spec (instruction-only plus included script). That is low-install-risk — nothing is downloaded or written by an installer. The script itself is included in the package.
!
Credentials
Registry metadata claims 'required binaries: none', but the script calls external tools (git via subprocess, and icacls on Windows). It also uses os.getlogin() and will commit using whatever Git credentials/config are present. No environment variables or credentials are requested in metadata, yet the script can modify a Git repo and change ACLs — this mismatch should be declared and explained.
Persistence & Privilege
always:false and no special persistence requested. The skill does not try to modify other skills or global agent settings. However, because model invocation is allowed by default, an agent could run the script (including with --fix) autonomously unless restricted — note for the user.
What to consider before installing
This tool will modify your workspace when run with --fix: it moves files into ./tmp, renames files under memory/, changes .ps1 ACLs on Windows, and will run git add/commit if a .git folder exists. Before installing or running: (1) review the included src/workspace_check.py source yourself; (2) run the script without --fix first to inspect its report; (3) back up your workspace or use a disposable/test repository; (4) ensure you understand which files the script considers 'non-essential' (it will move any root file not in its small whitelist); (5) be aware the package metadata does not declare required binaries (git, icacls), and the script will commit using your Git identity/config; (6) if you do not want autonomous modifications, restrict agent ability to invoke skills or disallow automated runs of this skill. If the developer intends automatic fixes, ask them to add a dry-run mode, explicit confirmation prompts, and to declare required binaries in the metadata.

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

latestvk975erj86f1hsg909c4q3gth2n858vhwmaintenancevk975erj86f1hsg909c4q3gth2n858vhwopsvk975erj86f1hsg909c4q3gth2n858vhwworkspacevk975erj86f1hsg909c4q3gth2n858vhw
77downloads
0stars
1versions
Updated 6d ago
v1.0.0
MIT-0

Workspace Auto Maintenance

技能描述

OpenClaw工作空间自动化运维技能,支持健康检查、自动修复常见问题,提升工作空间稳定性和整洁度。

核心功能

  1. 健康检查:自动扫描工作空间,计算健康分数,识别问题
  2. 自动修复:支持--fix参数自动修复常见问题:
    • 根目录冗余文件自动归档
    • 记忆文件命名规范自动修复
    • 脚本自动添加执行权限
    • Git更改自动提交
  3. 自定义规则:支持扩展自定义检查规则
  4. 跨平台支持:兼容Windows/Linux/macOS平台

安装方法

clawhub install workspace-auto-maintenance

使用方法

# 仅执行健康检查
python src/workspace_check.py

# 执行健康检查并自动修复问题
python src/workspace_check.py --fix

参数说明

  • --fix:开启自动修复模式,自动修复识别到的可修复问题
  • --threshold <分数>:自定义健康分数阈值,低于阈值时告警
  • --output <路径>:导出检查报告到指定路径

适配环境

  • OpenClaw v0.9+
  • Python 3.9+
  • 无额外依赖

发布信息

  • 作者:道一
  • 版本:v1.0.0
  • 发布日期:2026-04-21
  • 许可证:MIT

Comments

Loading comments...