Token导航 LogoToken导航

Agent Skill · 研究检索

mailtap(mailtap 搜索)

mailtap 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

mailtap 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 6,853。

总安装 20,740周安装 839GitHub Stars 公开资料未说明下载 6,511核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.4

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mailtap(mailtap 搜索)
来源仓库:https://github.com/zororaka00/mailtap
安装命令:
openclaw skills install mailtap
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install mailtap

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

生成和管理有效期为 30 分钟的临时一次性电子邮件地址,以便在无需身份验证的情况下接收和检索验证电子邮件和消息。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install mailtap;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

mailtap 怎么安装?

在终端执行 openclaw skills install mailtap。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mailtap 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

mailtap 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

mailtap 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

mailtap 用的人多吗?

公开数据是累计安装 20,740 次,近一周安装 839 次,下载 6,511 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

mailtap 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
mailtap

mailtap 搜索 · 本页

20,740—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

MailTap - Temporary Email Service

Version: 1.0.4\ Author: Web3 Hungry\ Author Handle: @zororaka00\ Author Profile: https://x.com/web3hungry\ Homepage: https://www.mailtap.org\ Category: Utilities → Automation → Privacy & Verification\ Tags: temporary-email

Overview

This skill provides seamless access to the MailTap Public API, a free temporary email service that generates disposable email addresses valid for 30 minutes.

No authentication or API key is required — all endpoints are public and use simple HTTP GET requests.

This skill does not store, proxy, or modify any email data. All operations communicate directly with the official MailTap public API.

Ideal for AI agents performing tasks such as:

  • Registering on websites/services without exposing real email addresses
  • Capturing verification codes, one-time links, or confirmation emails
  • Automating web3 airdrops, form submissions, or testing flows that require email verification
  • Privacy-focused workflows where email traceability must be avoided
  • Downloading email attachments when available

Base URL: https://api.mailtap.org

All responses are returned in JSON format.

Core Capabilities

The skill exposes three primary endpoints:

  1. Generate a new temporary email address
  2. Retrieve details of an existing email address
  3. Fetch all messages in the inbox (including attachments metadata)

Agents can chain operations autonomously (generate → wait → poll inbox → extract data → download attachments).

Usage Guide for Agents

Agents should use standard HTTP tools (curl, fetch, requests, etc.) to interact with the API.

1. Generate New Temporary Email

curl "https://api.mailtap.org/public/generate"

Example response:

{
  "address": "abc123xyz@mailtap.com",
  "expires_at": "2026-02-15T04:30:00.000Z",
  "created_at": "2026-02-15T04:00:00.000Z"
}

2. Get Email Details

curl "https://api.mailtap.org/public/email/{address}"

3. Get Inbox Messages

curl "https://api.mailtap.org/public/inbox/{address}"

Example response with attachment:

{
  "messages": [
    {
      "id": 1,
      "from_address": "no-reply@example.com",
      "subject": "Your document",
      "body": "Please find the attached file.",
      "received_at": "2026-02-15T04:05:00.000Z",
      "attachments": [
        {
          "filename": "document.pdf",
          "mime_type": "application/pdf",
          "size": 102400,
          "r2_key": "attachments/abc123/document.pdf"
        }
      ]
    }
  ]
}

4. Download Attachments

Attachments are publicly downloadable via the S3-compatible URL:

https://s3.mailtap.org/{r2_key}

Example:

curl -O "https://s3.mailtap.org/attachments/abc123/document.pdf"

or

wget "https://s3.mailtap.org/attachments/abc123/document.pdf"

Recommended Agent Workflow Patterns

Verification flow:

  1. Generate email
  2. Use for signup
  3. Poll inbox
  4. Extract verification code

Attachment flow:

  1. Poll inbox
  2. If attachments exist → download
  3. Process files

Error handling:

  • If 404 → email expired → generate new address

Example Prompts for Agents

  • "Generate a new temporary email using MailTap"
  • "Check inbox for abc123@mailtap.com and download attachments"
  • "Create temp email, wait up to 2 minutes, extract verification code"

Python Helper Library (Enhanced)

import requests
import time
import os
from pathlib import Path
from typing import Optional, Dict, Any

BASE_URL = "https://api.mailtap.org"
ATTACHMENT_BASE = "https://s3.mailtap.org"

# Whitelisted attachment types for security
WHITELISTED_MIME_TYPES = {
    "application/pdf",
    "image/jpeg", "image/png", "image/gif",
    "text/plain", "text/csv", "text/html",
    "application/msword", "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    "application/vnd.ms-excel", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
}

MAX_FILE_SIZE_MB = 10  # Maximum 10MB for security


def generate_email() -> Dict[str, Any]:
    """Generates a new temporary email address."""
    response = requests.get(f"{BASE_URL}/public/generate")
    response.raise_for_status()
    return response.json()


def get_inbox(address: str) -> Dict[str, Any]:
    """Retrieves the inbox for a given address."""
    response = requests.get(f"{BASE_URL}/public/inbox/{address}")
    if response.status_code == 404:
        return {"error": "Email not found or expired"}
    response.raise_for_status()
    return response.json()


def wait_for_message(address: str, timeout: int = 120, interval: int = 10) -> Dict[str, Any]:
    """Polls the inbox until a message arrives or timeout is reached."""
    start_time = time.time()
    while time.time() - start_time < timeout:
        inbox = get_inbox(address)
        if "error" not in inbox and inbox.get("messages"):
            return inbox["messages"][-1]
        time.sleep(interval)
    return {"error": "Timeout"}


def is_safe_attachment(attachment: Dict[str, Any]) -> bool:
    """Validates attachment safety based on MIME type and size."""
    mime_type = attachment.get("mime_type", "")
    size_mb = attachment.get("size", 0) / (1024 * 1024)
    
    if mime_type not in WHITELISTED_MIME_TYPES:
        return False
    if size_mb > MAX_FILE_SIZE_MB:
        return False
    return True


def download_attachment(r2_key: str, save_path: Optional[str] = None) -> str:
    """Downloads an attachment from the mailtap S3 storage with security checks."""
    
    # Parse attachment info from r2_key
    parts = r2_key.split("/")
    if len(parts) < 2:
        raise ValueError("Invalid r2_key format")
    
    filename = parts[-1]
    if not filename or ".." in filename:
        raise ValueError("Invalid filename detected")
    
    url = f"{ATTACHMENT_BASE}/{r2_key}"
    
    # Get attachment metadata first
    response = requests.head(url, allow_redirects=True)
    response.raise_for_status()
    
    # Validate content type and size
    content_type = response.headers.get("content-type", "")
    content_length = response.headers.get("content-length")
    
    if content_type not in WHITELISTED_MIME_TYPES:
        raise ValueError(f"Unsafe MIME type: {content_type}")
    
    if content_length:
        size_mb = int(content_length) / (1024 * 1024)
        if size_mb > MAX_FILE_SIZE_MB:
            raise ValueError(f"File too large: {size_mb:.1f}MB (max {MAX_FILE_SIZE_MB}MB)")
    
    # Download the file
    response = requests.get(url, stream=True)
    response.raise_for_status()
    
    if save_path is None:
        save_path = filename
    
    # Ensure safe save path
    save_path = Path(save_path)
    save_path = save_path.resolve()
    
    # Create directory if needed
    save_path.parent.mkdir(parents=True, exist_ok=True)
    
    with open(save_path, "wb") as f:
        for chunk in response.iter_content(8192):
            f.write(chunk)
    
    return str(save_path)


def list_attachments(address: str) -> list:
    """Lists all attachments in inbox with security validation."""
    inbox = get_inbox(address)
    if "error" in inbox:
        return []
    
    safe_attachments = []
    for message in inbox.get("messages", []):
        for attachment in message.get("attachments", []):
            if is_safe_attachment(attachment):
                safe_attachments.append(attachment)
    
    return safe_attachments

Security Enhancements

1. Attachment Validation

  • MIME Type Whitelisting: Only allows common safe file types (PDF, images, text, office documents)
  • Size Limitation: Maximum 10MB per file to prevent large file attacks
  • Filename Sanitization: Prevents path traversal attacks by validating filenames

2. Safe Download Process

  • Metadata Validation: Checks content type and size before downloading
  • Sandboxed Download: Uses safe path resolution to prevent directory traversal
  • Streamed Download: Downloads in chunks to prevent memory exhaustion

3. Agent Safety Guidelines

  • Never auto-execute: Agents should never automatically execute downloaded files
  • Validate before use: Always validate file type and content before processing
  • Use in sandbox: For untrusted files, use in isolated environment

Important Notes & Limitations

  • Emails expire automatically after 30 minutes.
  • Attachments are public.
  • No authentication required.
  • Rate limits are generous for normal usage.
  • Security-first approach: All downloads are validated for safety.
  • No automatic execution: Agents must manually validate and process files.
  • User responsibility: Users should still exercise caution with unknown attachments.

Example Secure Workflow

# Secure attachment handling
address = "test123@mailtap.com"

# Get inbox and list safe attachments
attachments = list_attachments(address)

for attachment in attachments:
    try:
        # Download with validation
        file_path = download_attachment(attachment["r2_key"])
        print(f"Downloaded safe file: {file_path}")
        
        # Process file (in sandbox if possible)
        # process_file(file_path)
        
    except Exception as e:
        print(f"Failed to download {attachment['filename']}: {e}")

Source & Verification

This skill is a transparent wrapper around the public MailTap API with enhanced security measures.

Disclaimer

Use responsibly and comply with MailTap terms of service. While security measures are implemented, users should still exercise caution when handling email attachments from unknown sources.

Created and maintained by Web3 Hungry. Updated for security compliance.

平台分布

OpenClaw

86.33%
按下载量换算5,621

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills