Skill Vetter Plus

该 Skill 对指定 AI Agent 技能目录做本地静态扫描，通过文本匹配检测 eval/exec、管道到 shell、破坏性命令、硬编码密钥、凭据文件访问、sudo 提权、Base64 混淆与网络调用等风险，支持控制台与 JSON 输出，并可统计跳过文件数。

certainlogicai

热度 51.08

最近更新 2026-07-12 22:45:58

分类：安全依赖：代码执行 / 读写文件应用场景：代码审查 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add skill-vetter-plus

Metadata

name: AI Agent Skill Scanner
version: 2.2.0
description: Security scanner for AI agent skills. Detects hardcoded secrets, unsafe code execution, prompt injection, and malware patterns in under 50ms. Scan before you install.
metadata: {"openclaw":{"emoji":"🔒","tags":["security","scanner","malware-detection","prompt-injection","secrets-detection","code-scanning","skill-safety"]}}

AI Agent Skill Scanner 🔒

Scan any skill for security issues before you install it. Detects hardcoded secrets, unsafe code execution, prompt injection, and malware patterns in under 50ms.

How to Use

# Scan any installed skill folder
python3 scripts/vetter.py /path/to/skill

# JSON output for scripting
python3 scripts/vetter.py /path/to/skill --json

What It Detects

Issue	Severity	What It Detects
`eval()` / `exec()`	Critical	Dynamic code execution
Pipe to shell	Critical	Commands piped directly to shell
Destructive commands	Critical	Filesystem destruction commands
`os.system()`	Critical	Shell command execution
Hardcoded API keys	High	Secret credential strings in code
Shell subprocess	High	Shell injection risk in subprocess
Hardcoded secrets	High	Auth tokens, credentials in code
Credential file access	High	Accessing config/credential directories
Sudo elevation	High	Commands requesting admin privileges
Base64 obfuscation	High	Encoded code execution
Git config access	High	Git config file reads
Password hardcoding	High	Password strings in code
Permission overrides	Medium	Overly permissive file mode changes
Network calls	Medium	Outbound network requests

New in v2.1

10 new detection signatures (pipe-to-shell, sudo escalation, destructive commands, credential file access, base64 obfuscation, git config, permission overrides)
Skips node_modules/, __pycache__/, .git/ (reduced false positives)
Smarter pipe-to-shell detection (only flags actual pipe patterns)
Self-scan exclusions (scanner ignores its own signatures file)
--verbose flag for skipped file counts

Example Result

Scanned 430 files in 368ms (skipped 6)
Found 1 issue(s):
  [CRITICAL] pipe-to-shell at install.sh:26
    → Remote code execution risk: downloading and piping to shell

Install

clawhub install ai-agent-skill-scanner

Notes

Text matching — won't catch obfuscated code
Always scan skills from unknown publishers before installing
Quick scan prevents accidents (50ms per skill)

Feedback

clawhub star ai-agent-skill-scanner — clawhub sync