可信 — 风险评分 0/100
上次扫描:1 天前 重新扫描
0 /100
agentmail
API-first email platform for AI agents — create/manage inboxes, send/receive emails, webhooks
AgentMail is a legitimate API-first email service skill with no malicious behavior detected. All capabilities are declared, documented, and consistent with its stated purpose of programmatic email management.
技能名称agentmail
分析耗时34.8s
引擎pi
可以安装
No action needed. The skill is safe to use as documented.
资源类型声明权限推断权限状态证据
网络访问 READ READ ✓ 一致 All HTTP calls go to api.agentmail.to REST endpoints
环境变量 READ READ ✓ 一致 AGENTMAIL_API_KEY read via os.getenv() in all scripts
文件系统 NONE READ ✓ 一致 send_email.py:81 reads attachment files for encoding; documented and necessary
命令执行 NONE NONE No subprocess calls in any script
技能调用 NONE NONE No cross-skill invocations
剪贴板 NONE NONE No clipboard access
浏览器 NONE NONE No browser automation
数据库 NONE NONE No direct database access
25 项发现
🔗
中危 外部 URL 外部 URL
https://console.agentmail.to
SKILL.md:20
🔗
中危 外部 URL 外部 URL
https://your-domain.com/webhook
SKILL.md:75
🔗
中危 外部 URL 外部 URL
https://api.agentmail.to/v0
references/API.md:3
🔗
中危 外部 URL 外部 URL
https://your-app.com/webhook/support
references/EXAMPLES.md:69
🔗
中危 外部 URL 外部 URL
https://your-app.com/webhook/tasks
references/EXAMPLES.md:225
🔗
中危 外部 URL 外部 URL
https://your-app.com/tasks/
references/EXAMPLES.md:306
🔗
中危 外部 URL 外部 URL
https://ngrok.com/
references/WEBHOOKS.md:87
🔗
中危 外部 URL 外部 URL
https://abc123.ngrok-free.app
references/WEBHOOKS.md:136
🔗
中危 外部 URL 外部 URL
https://abc123.ngrok-free.app/webhook
references/WEBHOOKS.md:151
🔗
中危 外部 URL 外部 URL
https://myapp.com/webhook
scripts/setup_webhook.py:7
📧
提示 邮箱 邮箱地址
[email protected]
SKILL.md:36
📧
提示 邮箱 邮箱地址
[email protected]
SKILL.md:84
📧
提示 邮箱 邮箱地址
[email protected]
SKILL.md:89
📧
提示 邮箱 邮箱地址
[email protected]
SKILL.md:102
📧
提示 邮箱 邮箱地址
[email protected]
references/API.md:35
📧
提示 邮箱 邮箱地址
[email protected]
references/API.md:159
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:297
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:404
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:428
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:428
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:440
📧
提示 邮箱 邮箱地址
[email protected]
references/EXAMPLES.md:497
📧
提示 邮箱 邮箱地址
[email protected]
references/WEBHOOKS.md:18
📧
提示 邮箱 邮箱地址
[email protected]
scripts/check_inbox.py:7
📧
提示 邮箱 邮箱地址
[email protected]
scripts/send_email.py:6

目录结构

8 文件 · 49.0 KB · 1729 行
Markdown 4f · 1219L Python 3f · 505L JSON 1f · 5L
├─ 📁 references
│ ├─ 📝 API.md Markdown 229L · 4.3 KB
│ ├─ 📝 EXAMPLES.md Markdown 508L · 13.8 KB
│ └─ 📝 WEBHOOKS.md Markdown 294L · 7.2 KB
├─ 📁 scripts
│ ├─ 🐍 check_inbox.py Python 213L · 7.6 KB
│ ├─ 🐍 send_email.py Python 113L · 3.9 KB
│ └─ 🐍 setup_webhook.py Python 179L · 6.0 KB
├─ 📋 _meta.json JSON 5L · 128 B
└─ 📝 SKILL.md Markdown 188L · 5.9 KB

依赖分析 2 项

包名版本来源已知漏洞备注
agentmail unpinned pip Python SDK installed via pip; version not pinned in SKILL.md install instruction
flask unpinned pip Optional dev dependency for webhook test server only

安全亮点

✓ No subprocess or shell execution — all operations use the agentmail SDK
✓ No credential exfiltration — AGENTMAIL_API_KEY is read only to initialize the SDK client
✓ No sensitive file access — no reads of ~/.ssh, ~/.aws, .env, or similar paths
✓ No obfuscation — no base64, eval, or encoded payloads
✓ No external IP connections — all API calls go to api.agentmail.to (documented service)
✓ No curl|bash or wget|sh remote script execution
✓ No hidden functionality — code matches SKILL.md documentation
✓ Proactive prompt injection awareness — SKILL.md documents webhook-based prompt injection risks and recommends Clawdbot allowlist filters
✓ Well-structured scripts with proper error handling and dependency checks
✓ Local webhook test server (Flask on localhost:3000) is development-only and clearly scoped