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许可证需确认审计提醒

clawsec-clawhub-checkerclawsec ClawHub checker 搜索

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

4,134

周安装

174

GitHub Stars

962

下载量

1,448
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

unknown

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:clawsec-clawhub-checker(clawsec ClawHub checker 搜索)
来源仓库:https://github.com/prompt-security/clawsec
仓库路径:skills/clawsec-clawhub-checker
安装命令:
npx skills add https://github.com/prompt-security/clawsec --skill clawsec-clawhub-checker
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。

skills.shnpx skills
npx skills add https://github.com/prompt-security/clawsec --skill clawsec-clawhub-checker

简介

执行安全扫描以识别提示相关的潜在风险。

  • 检查敏感信息泄露、权限滥用等安全问题。
  • 输出详细的漏洞描述与修复指引。clawsec-clawhub-checker 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 支持命令行调用和持续集成环境嵌入。
  • 检测结果需人工复核确认,不可全信工具判断。

SKILL.md

ClawSec ClawHub Checker

Adds a reputation gate on top of the clawsec-suite guarded installer.

Operational Notes

  • Required runtime: node, clawhub, openclaw
  • Depends on: installed clawsec-suite
  • Side effects: none on other skills; this package does not rewrite installed suite files
  • Advisory-hook wiring is optional and manual in this release
  • Network behavior: reputation checks call ClawHub inspect/search endpoints
  • Trust model: scores are heuristic and confirmation-gated

What It Does

  1. Reads skill metadata from ClawHub (inspect --json)
  2. Evaluates scanner status (including VirusTotal summary when present)
  3. Applies additional reputation heuristics (age, updates, author history, downloads)
  4. Requires explicit --confirm-reputation when score is below threshold

Installation

Install after clawsec-suite:

npx clawhub@latest install clawsec-suite
npx clawhub@latest install clawsec-clawhub-checker

Optional preflight check (validates local paths and prints recommended command):

node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/setup_reputation_hook.mjs

Usage

Run the enhanced installer directly from this skill:

node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/enhanced_guarded_install.mjs \
  --skill some-skill \
  --version 1.0.0

If a skill is below threshold, rerun only with explicit approval:

node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/enhanced_guarded_install.mjs \
  --skill some-skill \
  --version 1.0.0 \
  --confirm-reputation

Optional Advisory-Hook Wiring (Manual)

This release does not auto-patch clawsec-suite hook files. If you rely on advisory alerts that include reputationWarning / reputationWarnings, wire the checker module manually:

  • Source module: ~/.openclaw/skills/clawsec-clawhub-checker/hooks/clawsec-advisory-guardian/lib/reputation.mjs
  • Target hook file: ~/.openclaw/skills/clawsec-suite/hooks/clawsec-advisory-guardian/handler.ts

Treat that wiring as a deliberate local customization and review it before enabling.

Exit Codes

  • 0 safe to install
  • 42 advisory confirmation required (from clawsec-suite)
  • 43 reputation confirmation required
  • 1 error

Configuration

Environment variables:

  • CLAWHUB_REPUTATION_THRESHOLD - Minimum score (0-100, default: 70)

Safety Notes

  • This is defense-in-depth, not a replacement for advisory matching
  • Scanner outputs can produce false positives and false negatives
  • Always review skill code before overriding warnings

Development

Key files:

  • scripts/enhanced_guarded_install.mjs
  • scripts/check_clawhub_reputation.mjs
  • scripts/setup_reputation_hook.mjs
  • hooks/clawsec-advisory-guardian/lib/reputation.mjs

License

GNU AGPL v3.0 or later - Part of the ClawSec security suite

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

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

展示第三方安全扫描或审计结果

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

Codex

34.62%
按下载量换算501

Claude

30.86%
按下载量换算447

Cursor

17.99%
按下载量换算260

Gemini CLI

9.93%
按下载量换算144

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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