Skill flagged — suspicious patterns detected

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

Permission Manager

v1.0.0

审批权限管理技能 - 快速切换不同审批模式(白名单/完整权限/免审批)

0· 69·0 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/permission-manager.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Permission Manager" (jirboy/permission-manager) from ClawHub.
Skill page: https://clawhub.ai/jirboy/permission-manager
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 permission-manager

ClawHub CLI

Package manager switcher

npx clawhub@latest install permission-manager
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description align with behavior: the code and SKILL.md both implement switching approval modes and reading/writing OpenClaw config. However, the skill metadata claimed no required config paths while both SKILL.md and permission_switch.py explicitly read/write ~/.openclaw/openclaw.json and ~/.openclaw/exec-approvals.json — this mismatch is an incoherence that should have been declared.
Instruction Scope
SKILL.md confines actions to changing approval-related settings and instructs to require human consent for the 'no approval' mode. The included Python implementation directly edits the user's OpenClaw config files and provides a subprocess wrapper. There is a small mismatch: the docs suggest using 'openclaw config set ...' CLI commands, while the script edits the JSON file directly. The instructions do not attempt to read other unrelated files or environment secrets.
Install Mechanism
No install spec and no external downloads; only an instruction file and a local Python script are included. No network fetches or package installs are present in the provided files.
!
Credentials
The skill declares no required env vars or config paths in registry metadata, but in practice it reads/writes user config at ~/.openclaw/openclaw.json and exec-approvals.json. That undeclared access to per-user configuration is a proportionality/coherence issue: the skill needs access to those files to work, and that should be explicitly declared so users can evaluate impact.
!
Persistence & Privilege
The skill is not force-included (always:false) but is invocable and model-invocation is allowed by default. Because it can change the agent's command-approval policy (including turning approvals off), autonomous invocation combined with this capability is high-impact: a model or another skill could invoke it to disable approvals. SKILL.md recommends human confirmation for disabling approvals, but that is an instruction-level safeguard — it may not be enforceable by the platform. Consider requiring human gating or forbidding autonomous switching to 'no_approval'.
What to consider before installing
This skill appears to implement exactly what it says (switching approval modes) but you should be cautious before installing: 1) It reads and writes your per-user OpenClaw config files (~/.openclaw/openclaw.json and exec-approvals.json) even though the registry metadata didn't declare those paths — expect the skill to modify local config. 2) The skill can disable all approvals (no-approval mode); ensure human confirmation is enforced by policy (don’t allow autonomous invocation to flip approvals off). 3) Review the included permission_switch.py yourself (or with a technical person) to confirm it only modifies the intended keys and does not perform network calls or unexpected actions. 4) Back up your ~/.openclaw/ directory before using, test in a non-production environment, and restrict the skill so it cannot be auto-run to escalate privileges without explicit human authorization.

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

latestvk97b8d51qpkgvhjv5bgg2ztpph84ydv2
69downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

审批权限管理技能

功能说明

快速切换 OpenClaw 的审批权限模式,适应不同使用场景。

支持模式:

  • 🔒 默认权限(白名单模式) - 安全,推荐日常使用
  • 完整权限 - 平衡,适合开发测试
  • 🚀 免审批模式 - 便利,适合可信环境

使用方式

对智能体说:

1️⃣ 切换到默认权限

按默认权限设置
切换到白名单模式
恢复默认审批

效果:

  • security = allowlist
  • ask = on-miss
  • ✅ 白名单内的命令自动执行
  • ✅ 其他命令需要审批
  • 🛡️ 最安全,推荐日常使用

2️⃣ 切换到完整权限

完整权限
切换到开发模式
给我完整权限

效果:

  • security = full
  • ask = on-miss
  • ✅ 所有命令自动执行
  • ✅ 保留审批记录
  • ⚠️ 适合开发测试

3️⃣ 切换到免审批模式

⚠️ 警告:此模式会关闭所有命令审批,存在安全风险!

触发语句:

免审批模式
关闭所有审批
切换到便利模式

效果:

  • security = full
  • ask = off
  • ✅ 所有命令自动执行
  • ✅ 无需任何审批
  • 🔴 ⚠️ 仅限可信环境!执行前必须获得人类明确同意

执行流程:

  1. 告知人类风险:"切换到免审批模式将关闭所有命令审批,任何命令都将自动执行,存在安全风险。"
  2. 等待人类明确同意
  3. 执行配置命令
  4. 完成后提醒人类尽快恢复审批模式

4️⃣ 查看当前权限

当前权限设置
查看审批模式
现在是什么权限

效果: 显示当前配置状态


5️⃣ 自定义配置

设置 security 为 allowlist,ask 为 always
切换到严格模式

权限模式对比

模式securityask安全性便利性推荐场景
默认权限allowliston-miss⭐⭐⭐⭐⭐⭐⭐日常使用、生产环境
完整权限fullon-miss⭐⭐⭐⭐⭐⭐⭐开发、测试、调试
免审批fulloff⭐⭐⭐⭐⭐可信环境、演示
严格模式allowlistalways⭐⭐⭐⭐⭐⭐高安全需求

执行流程

步骤 1:识别用户意图

关键词匹配:

  • "默认权限"、"白名单" → allowlist + on-miss
  • "完整权限"、"开发模式" → full + on-miss
  • "免审批"、"关闭审批" → full + off
  • "严格模式" → allowlist + always

步骤 2:执行配置命令

命令:

openclaw config set tools.exec.security <模式>
openclaw config set tools.exec.ask <策略>

步骤 3:确认生效

验证:

  • 读取当前配置
  • 显示给用户确认
  • 提示是否需要重启 Gateway

步骤 4:保存预设(可选)

记录到记忆:

  • 用户偏好模式
  • 常用场景配置

输出格式

切换成功

✅ 权限已切换到:默认权限(白名单模式)

当前配置:
- security: allowlist
- ask: on-miss

说明:白名单内的命令自动执行,其他命令需要审批。
建议:日常使用推荐此模式,安全且便利。

切换失败

❌ 权限切换失败

错误信息:[具体错误]

建议:
1. 检查 Gateway 是否正常运行
2. 尝试重启 Gateway 后重试
3. 手动编辑配置文件

查看当前权限

📊 当前权限设置

模式:完整权限
配置:
- security: full
- ask: on-miss

说明:所有命令自动执行,保留审批记录。
适用场景:开发、测试、调试

安全说明

⚠️ 风险提示

模式风险建议
默认权限🟢 低推荐日常使用
完整权限🟡 中开发测试使用
免审批🔴 高仅限可信环境

🛡️ 最佳实践

  1. 日常使用默认权限 - 平衡安全性和便利性
  2. 开发时临时切换 - 完成后立即恢复默认
  3. 避免长期使用免审批 - 存在安全风险
  4. 定期审查配置 - 确保符合安全策略

配置持久化

配置文件位置

~/.openclaw/openclaw.json  # 全局配置(审批策略)
~/.openclaw/exec-approvals.json  # 具体命令审批记录

配置字段

{
  "tools": {
    "exec": {
      "security": "allowlist|full",
      "ask": "off|on-miss|always"
    }
  }
}

生效方式

  • 立即生效: 当前会话
  • 持久生效: 需要重启 Gateway
  • 命令记录: exec-approvals.json 存储已批准的具体命令

示例对话

示例 1:切换到免审批

用户:切换到免审批模式

智能体:✅ 权限已切换到:免审批模式

当前配置:
- security: full
- ask: off

说明:所有命令自动执行,无需任何审批。
⚠️ 注意:此模式安全性较低,仅用于可信环境。

需要重启 Gateway 使配置完全生效吗?

示例 2:恢复默认

用户:按默认权限设置

智能体:✅ 权限已切换到:默认权限(白名单模式)

当前配置:
- security: allowlist
- ask: on-miss

说明:白名单内的命令自动执行,其他命令需要审批。
🛡️ 推荐:日常使用此模式,安全且便利。

示例 3:查看当前权限

用户:现在是什么权限

智能体:📊 当前权限设置

模式:完整权限
配置:
- security: full
- ask: on-miss

说明:所有命令自动执行,保留审批记录。
适用场景:开发、测试、调试

相关技能

  • exec-approvals - 审批列表管理
  • gateway-manager - Gateway 管理
  • config-editor - 配置文件编辑
  • security-audit - 安全审计

注意事项

  1. Gateway 重启: 某些配置需要重启 Gateway 才能完全生效
  2. 会话隔离: 配置可能对当前会话立即生效,但新会话需要重启
  3. 安全审计: 建议定期审查权限配置
  4. 备份配置: 切换前建议备份配置文件

版本历史

  • v1.0.0 (2026-04-03) - 初始版本

Comments

Loading comments...