可信 — 风险评分 5/100
上次扫描:22 小时前 重新扫描
5 /100
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Documentation-only skill describing the legitimate open-source agent-browser CLI tool by Vercel Labs; no executable code present.
技能名称agent-browser
分析耗时25.1s
引擎pi
可以安装
This skill is safe to use. No security concerns identified.
资源类型声明权限推断权限状态证据
文件系统 NONE NONE No code present - documentation describes state save/load as expected browser au…
网络访问 NONE NONE No code present - network commands described as expected browser automation beha…
命令执行 NONE NONE No code present - describes CLI commands to be executed by external agent-browse…
浏览器 READ READ ✓ 一致 SKILL.md: browser automation (open, click, fill, snapshot)
环境变量 NONE NONE No environment variable access in skill documentation
技能调用 NONE NONE No skill chaining described
剪贴板 NONE NONE No clipboard access described
数据库 NONE NONE No database access described
1 项发现
🔗
中危 外部 URL 外部 URL
https://www.google.com
SKILL.md:168

目录结构

2 文件 · 5.6 KB · 211 行
Markdown 1f · 206L JSON 1f · 5L
├─ 📋 _meta.json JSON 5L · 141 B
└─ 📝 SKILL.md Markdown 206L · 5.4 KB

安全亮点

✓ Documentation-only skill with no executable code
✓ References legitimate open-source tool (Vercel Labs agent-browser on GitHub)
✓ All described capabilities are standard browser automation features
✓ No hidden functionality or shadow behavior
✓ No credential harvesting, data exfiltration, or obfuscation patterns
✓ No base64-encoded content or suspicious string patterns
✓ No curl|bash or wget|sh remote script execution
✓ No access to sensitive paths (~/.ssh, ~/.aws, .env)