Agent 专用邮箱统一管理：让 Claude Code、Codex 等平台的 Agent 用一套命令收发邮件、整理收件箱、分发任务。支持网易 ClawEmail（claw.163.com）和腾讯 Agent Mail（QQ 邮箱，agent.qq.com）两家后端，通过 MAIL_PROVIDER 切换。当用户提到收发邮件、看收件箱、搜索邮件、回复转发邮件、下载附件、整理邮件、给其他 Agent 派邮件任务、配置 Agent 邮箱、腾讯 QQ 邮箱 Agent、网易 ClawEmail 时使用此 skill。
Ask your Agent
Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/agent-email
This session only. Nothing lands on disk.
≈131 tokens on demand. Your agent reads this file only when SKILL.md points to it.
Agent 回复邮件时可参考以下模板结构。
收件人: {{sender_email}}
主题: Re: {{original_subject}}
{{agent_name}} 已收到您的邮件，处理结果如下：
## 处理摘要
{{summary}}
## 详细结果
{{details}}
---
此邮件由 AI Agent ({{agent_email}}) 自动发送收件人: {{recipient_email}}
主题: [通知] {{notification_title}}
{{notification_body}}
---
此邮件由 AI Agent ({{agent_email}}) 自动发送Source: SKILL.md on GitHub
This skill enables an AI agent to manage emails through NetEase ClawEmail and Tencent Agent Mail. While it follows best practices by including defensive instructions against prompt injection from incoming emails, it inherently creates an indirect prompt injection surface by ingesting external content. It also possesses the capability to read local files and send them externally as email bodies, which is standard for an email tool but requires user oversight.
No alerts
Risk: MEDIUM · 2 issues
Signed by skilld at 1c459c4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.