ClawAudit — Security Auditor for Agent Skills
Static security analyzer for OpenClaw SKILL.md files. Detects prompt injection, credential exfiltration, obfuscated payloads, and dangerous capability combinations before you install.
What It Does
Paste or pipe any SKILL.md content and get back a trust score (0-100) with detailed findings.
Detects:
- - Prompt injection and agent manipulation (including Unicode homoglyph evasion)
- Data exfiltration patterns (HTTP, DNS, encoded channels)
- Dangerous shell commands (curl|sh, /dev/tcp, process substitution)
- Credential harvesting (env vars, SSH keys, API tokens)
- Obfuscated payloads (base64, hex escapes, eval chains)
- Compound threats (e.g. file read + network out = exfiltration)
- Permission mismatches (undeclared capabilities)
Zone-aware analysis — understands markdown structure. Code blocks are weighted as executable instructions. Security documentation describing threats is not flagged as a threat itself.
Usage
Audit a skill before installing:
CODEBLOCK0
Or POST raw skill content:
CODEBLOCK1
Trust Tiers
| Score | Tier | Meaning |
|---|
| 80-100 | Trusted | No significant issues found |
| 60-79 |
Moderate | Minor concerns, review recommended |
| 40-59 | Suspicious | Significant issues, use with caution |
| 0-39 | Dangerous | Critical threats detected, do not install |
Response Format
CODEBLOCK2
About
Built by 4Worlds. Zone-aware static analysis with 60+ detection patterns, Unicode homoglyph normalization, and compound threat detection.
ClawAudit — 代理技能安全审计工具
针对OpenClaw SKILL.md文件的静态安全分析器。在安装前检测提示注入、凭证窃取、混淆载荷及危险能力组合。
功能说明
粘贴或管道输入任意SKILL.md内容,即可获得信任评分(0-100分)及详细分析结果。
检测项:
- - 提示注入与代理操控(包括Unicode同形字符规避)
- 数据窃取模式(HTTP、DNS、编码通道)
- 危险shell命令(curl|sh、/dev/tcp、进程替换)
- 凭证收集(环境变量、SSH密钥、API令牌)
- 混淆载荷(base64、十六进制转义、eval链)
- 复合威胁(如文件读取+网络输出=数据窃取)
- 权限不匹配(未声明的能力)
区域感知分析 — 理解Markdown结构。代码块被加权为可执行指令。描述威胁的安全文档本身不会被标记为威胁。
使用方法
安装前审计技能:
bash
curl -s https://clauwdit.4worlds.dev/audit/author/skill-name
或POST原始技能内容:
bash
curl -s -X POST https://clauwdit.4worlds.dev/audit \
-H Content-Type: application/json \
-d {skill:author/skill-name}
信任等级
| 分数 | 等级 | 含义 |
|---|
| 80-100 | 可信 | 未发现重大问题 |
| 60-79 |
中等 | 存在轻微问题,建议审查 |
| 40-59 | 可疑 | 存在重大问题,谨慎使用 |
| 0-39 | 危险 | 检测到严重威胁,请勿安装 |
响应格式
json
{
trust: { score: 85, tier: trusted },
findings: [
{
severity: medium,
description: 检测到网络请求能力,
zone: code,
line: 12
}
],
capabilities: [networkout, fileread],
compoundThreats: [],
permissionIntegrity: { undeclared: [], unused: [] }
}
关于
由4Worlds构建。采用区域感知静态分析,包含60+检测模式、Unicode同形字符归一化及复合威胁检测功能。