Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问clear审计未展示

clawdbot-security爪机器人安全

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

194

周安装

8

GitHub Stars

公开资料未说明

下载量

63
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:clawdbot-security(爪机器人安全)
来源仓库:https://github.com/spanishflu-est1918/clawdbot-security
仓库路径:skills/clawdbot-security
安装命令:
npx skills add spanishflu-est1918/clawdbot-security --skill "clawdbot-security"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add spanishflu-est1918/clawdbot-security --skill "clawdbot-security"

简介

clawdbot-security 用于辅助安全审计、权限检查和认证流程分析。

  • 适合梳理敏感配置、检查依赖风险和生成安全复核清单。
  • 通过 npx skills add spanishflu-est1918/clawdbot-security --skill "clawdbot-security" 安装,需结合原始 README 核验具体用法。
  • 使用时不能将工具输出直接作为最终结论,涉及密钥或用户数据时应先确认最小权限。
  • 注意脱敏方式和操作边界,避免在生产系统中执行高风险操作。

SKILL.md

name
clawdbot-security
description
Security hardening for Clawdbot Gateway. Use when running security audits, interpreting audit findings, configuring DM/group policies, setting up sandboxing, managing elevated tools, extracting secrets to .env, or responding to security incidents. Also triggers on questions about prompt injection defense, access control, network exposure, or the three-layer security model (sandbox, tool policy, elevated).

Clawdbot Security

Harden Clawdbot Gateway deployments by fetching current security practices and applying them.

Fetch Current Docs First

Before advising on security, fetch the latest official documentation:

# Primary security guide
web_fetch https://raw.githubusercontent.com/clawdbot/clawdbot/main/docs/gateway/security.md

# Specific topics
web_fetch https://raw.githubusercontent.com/clawdbot/clawdbot/main/docs/gateway/sandboxing.md
web_fetch https://raw.githubusercontent.com/clawdbot/clawdbot/main/docs/gateway/authentication.md
web_fetch https://raw.githubusercontent.com/clawdbot/clawdbot/main/docs/gateway/pairing.md

Quick Commands

clawdbot security audit           # Basic check
clawdbot security audit --deep    # Live Gateway probe
clawdbot security audit --fix     # Auto-apply safe fixes
clawdbot sandbox explain          # Debug sandbox/tool policy

Decision Tree

User needs help with security
├── Running audit or interpreting findings?
│   └── Run `clawdbot security audit`, explain findings, suggest fixes
├── Configuring access control (DM/group policies)?
│   └── Fetch security.md, explain pairing vs allowlist vs open
├── Setting up sandboxing?
│   └── Fetch sandboxing.md, explain mode/scope/workspaceAccess
├── Managing secrets in config?
│   └── Run scripts/extract_secrets.py or guide manual .env creation
├── Responding to incident?
│   └── Follow contain → rotate → audit workflow
└── General security question?
    └── Fetch security.md, consult references/quick-reference.md

Three-Layer Model (Quick Summary)

  1. Sandbox — Where tools run (Docker vs host)
  2. Tool Policy — Which tools are allowed
  3. Elevated — Exec-only host escape hatch

For details, read references/quick-reference.md.

Extract Secrets Script

Automate moving hardcoded secrets from config to .env:

python scripts/extract_secrets.py --dry-run  # Preview
python scripts/extract_secrets.py            # Execute

Audit Priority Order

  1. Open groups + tools → Lock down with allowlists
  2. Network exposure → Fix immediately
  3. Browser control → Require token auth
  4. File permissionschmod 600 config, chmod 700 dirs
  5. Plugins → Only load trusted ones
  6. Model choice → Use instruction-hardened models (Opus 4.5)

Incident Response

  1. Contain: Stop gateway, bind: "loopback", freeze policies
  2. Rotate: gateway.auth.token, API keys, browser control token
  3. Audit: Check logs (/tmp/clawdbot/*.log) and transcripts
  4. Re-run: clawdbot security audit --deep

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

windsurf

29.75%
按下载量换算19

clawdbot

23.13%
按下载量换算15

OpenCode

19.89%
按下载量换算13

Cursor

13.26%
按下载量换算8

Claude Code

8.65%
按下载量换算5

Gemini CLI

3.54%
按下载量换算2

安全审计

暂无安全审计结果可展示。

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills