← 返回 Skills 市场
zaddy6

Agent Email

作者 Isaac David · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
516
总下载
1
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-email-cli
功能描述
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the u...
使用说明 (SKILL.md)

Agent Email CLI

Overview

Use this skill to operate the agent-email command safely and predictably for agent workflows that need inbox access.

Prefer JSON-native command output and return key fields (email, messageId, subject, createdAt, from.address) in your summaries.

Workflow

  1. Verify CLI availability.
command -v agent-email
agent-email --help

If missing, install:

npm install -g @zaddy6/agentemail
# or
bun install -g @zaddy6/agentemail
  1. Create a mailbox account.
agent-email create

Record these fields from JSON output:

  • data.email
  • data.accountId
  • data.activeEmail

Do not record, repeat, or print secret values such as mailbox passwords or tokens.

  1. Read latest messages.
agent-email read \x3Cemail|default>

For inbox waiting/polling:

agent-email read \x3Cemail|default> --wait 30 --interval 2

For full message payloads:

agent-email read \x3Cemail|default> --full
  1. Retrieve one message in detail.
agent-email show \x3Cemail|default> \x3CmessageId>

Use show when you need body/source details for verification links, codes, or full content extraction.

  1. Manage mailbox profiles.
agent-email accounts list
agent-email use \x3Cemail|default>
agent-email accounts remove \x3Cemail>

Avoid commands that require entering secrets on the command line in agent logs.

  1. Delete processed/irrelevant message when requested.
agent-email delete \x3Cemail|default> \x3CmessageId>

Operational Guidance

  • Keep command output machine-readable; avoid forcing human output unless requested.
  • Prefer default alias when user does not specify an email.
  • Never echo, store, or summarize secret values (password, token) from command output.
  • If command fails, surface the JSON error code and hint fields directly.
  • For auth failures (AUTH_REQUIRED/401), rerun command once and request user intervention if credentials must be re-established.
  • For rate limits (RATE_LIMITED/429), retry after short delay.

Troubleshooting

  • command not found: ensure ~/.bun/bin or npm global bin path is on PATH.
  • NO_ACTIVE_ACCOUNT: run agent-email create or agent-email use \x3Cemail>.
  • ACCOUNT_NOT_FOUND: run agent-email accounts list and pick a valid address.
  • EOTP during npm publish: use npm trusted publishing for CI or publish locally with OTP.

References

安全使用建议
This skill appears coherent for driving a disposable-mail CLI. Before installing or running it: (1) vet the npm package @zaddy6/agentemail — inspect its source repository and published package contents (postinstall scripts, network calls); (2) prefer installing in a sandboxed environment (container/VM) or audit the package locally rather than a global npm install; (3) avoid having the agent print or log any returned 'password' or 'token' fields and review CLI outputs for unexpected endpoints or data exfiltration behavior; (4) if you cannot review the package, use a trusted alternative or manually run the CLI yourself rather than giving autonomous agent access.
功能分析
Type: OpenClaw Skill Name: agent-email-cli Version: 1.0.0 The skill is classified as suspicious primarily due to its instruction to install an external, globally-scoped npm/bun package (`@zaddy6/agentemail`) via `npm install -g` or `bun install -g` as detailed in `SKILL.md`. While the stated purpose of the skill (operating an email CLI) is benign, relying on and installing an external dependency from a public registry introduces a significant supply chain vulnerability. If the `@zaddy6/agentemail` package were compromised, the agent would execute malicious code with global permissions. Although the skill's instructions explicitly warn against handling secrets, the inherent risk of installing arbitrary external code makes it suspicious rather than benign.
能力评估
Purpose & Capability
The name/description match the runtime instructions: all actions are limited to driving an 'agent-email' CLI (create/read/show/delete/accounts). The SKILL.md does not request unrelated credentials, files, or system-wide configuration.
Instruction Scope
Instructions are narrowly scoped to running the CLI, preferring JSON output and explicitly warning not to print/store secret fields. They do not instruct reading arbitrary files, environment variables, or posting data to third-party endpoints from the agent itself.
Install Mechanism
There is no formal install spec in the registry (instruction-only), but the SKILL.md recommends installing @zaddy6/agentemail via npm or bun if the CLI is missing. Installing an unvetted npm package globally can execute arbitrary code (postinstall scripts) and should be reviewed before installation.
Credentials
The skill declares no required env vars, credentials, or config paths. The only path hints are about npm/bun global bin on PATH which are proportional to making the CLI available.
Persistence & Privilege
The skill does not request persistent 'always' inclusion and contains no instructions to modify other skills or system-wide agent settings; autonomous invocation is allowed but is the platform default.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install agent-email-cli
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agent-email-cli 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of agent-email-cli skill. - Enables creating and managing disposable inboxes via the agent-email CLI. - Supports polling for new mail, retrieving message details, and mailbox profile management. - Offers operational guidance for safe command usage and error handling. - Focuses on JSON-native output and handling of key message fields.
元数据
Slug agent-email-cli
版本 1.0.0
许可证
累计安装 5
当前安装数 4
历史版本数 1
常见问题

Agent Email 是什么?

Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the u... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 516 次。

如何安装 Agent Email?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-email-cli」即可一键安装,无需额外配置。

Agent Email 是免费的吗?

是的,Agent Email 完全免费(开源免费),可自由下载、安装和使用。

Agent Email 支持哪些平台?

Agent Email 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agent Email?

由 Isaac David(@zaddy6)开发并维护,当前版本 v1.0.0。

💬 留言讨论