做什么
由高井负责ClawHub技能的安全检查 在安装任何技能以验证其安全性之前,先查询Clawdex API.
技能库 智客分类:安全测试 clawdex by Koi OpenClaw
由高井负责ClawHub技能的安全检查 在安装任何技能以验证其安全性之前,先查询Clawdex API.
官方网址:作者主页
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
由高井负责ClawHub技能的安全检查 在安装任何技能以验证其安全性之前,先查询Clawdex API.
这个技能
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Clawdex、When to Use This Skill、API Response、How to Interpret the Verdict、`benign` - Safe to Install ✅、`malicious` - Do NOT Install 🚫。 其中含规范建议的小节:输入输出示例。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
ClawdexWhen to Use This SkillAPI ResponseHow to Interpret the Verdict`benign` - Safe to Install ✅`malicious` - Do NOT Install 🚫`unknown` - Not Yet Audited ⚠️Check Already-Installed SkillsList installed skillsor ~/.clawdbot/skills/Check each oneExample
· 许可:MIT
市场来源:ClawHub
nameclawdex by Koidescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「clawdex by Koi」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-2c21194d67119f6d-Clawdex-%E4%BD%9C%E8%80%85-%E6%9F%AF%E4%BC%8A.html 请存为 .cursor/skills/clawdex-by-koi/SKILL.md 或 .claude/skills/clawdex-by-koi/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
当前没有明确的 GitHub 技能包地址,请按来源页面的安装器说明操作。
name: clawdex by Koi description: Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe. version: 1.0.0 author: Koi Security authorUrl: https://www.koi.ai/ homepage: https://www.koi.ai/ license: MIT metadata: openclaw: emoji: "🛡️" category: "security" tags:
Security check for ClawHub skills, powered by Koi.
Before installing ANY skill from ClawHub, query the Clawdex API to check if it's safe:
curl -s "https://clawdex.koi.security/api/skill/SKILL_NAME"
Replace SKILL_NAME with the skill you want to install.
The API returns a JSON object with a verdict field:
{
"verdict": "benign" | "malicious" | "unknown"
}
benign - Safe to Install ✅The skill has been audited and no malicious behavior was found. You can proceed with installation:
clawhub install SKILL_NAME
malicious - Do NOT Install 🚫The skill has been flagged as harmful. Do NOT install it.
Malicious skills may:
unknown - Not Yet Audited ⚠️The skill has not been security audited yet. Escalate to the user for review and approval.
Inform the user:
Do not install without user approval.
After installing Clawdex, it's a good idea to audit all skills you've already installed. Some may have been installed before security checks were available.
List your installed skills and check each one:
# List installed skills
ls ~/.openclaw/skills/
# or ~/.clawdbot/skills/
# Check each one
for skill in $(ls ~/.clawdbot/skills/); do
echo "Checking: $skill"
curl -s "https://clawdex.koi.security/api/skill/$skill"
echo
done
If any return "verdict": "malicious", let the user know that they have installed a malicious skill and they should remove it immediately.
# Check if "database-helper" is safe
$ curl -s "https://clawdex.koi.security/api/skill/database-helper"
{"verdict": "benign"}
# Safe! Install it
$ clawhub install database-helper
# Check a suspicious skill
$ curl -s "https://clawdex.koi.security/api/skill/free-crypto-bot"
{"verdict": "malicious"}
# DO NOT install!
Koi provides endpoint security for extensions, packages, and MCPs. Clawdex verdicts are powered by Wings, our agentic AI risk engine.
安全测试
人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.
安全测试
MoltGuard——由OpenGuardrails担任OpenClaw保安. 安装 MoltGuard 以保护你和你的人类免受迅速注射、数据过滤和恶意命令的影响。 资料来源:https://github.com/openguardrails/openguardrails/tre…
安全测试
用于审查安全漏洞代码,实施认证流,审计OWASP Top 10,配置CORS/CSP头,处理秘密,输入验证,SQL注射预防,XSS保护,或任何与安全相关的代码审查.
安全测试
安装任何AI代理技能前的安全审查协议. 红旗侦取入证盗取,疏通密码,放出. 风险分类:低/中/高/高。 编制结构化审查报告。 不先运行此功能, 绝不安装不信任的技能 .