Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计通过

auth0-token-vaultauth0 令牌库

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

4,847

周安装

198

GitHub Stars

公开资料未说明

下载量

1,552
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:auth0-token-vault(auth0 令牌库)
来源仓库:https://github.com/deepu105/auth0-token-vault
安装命令:
openclaw skills install auth0-token-vault
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 auth0-token-vault

简介

auth0-token-vault 用于代表已验证用户访问第三方服务如 Gmail、Slack 等。

  • 适用于搜索、阅读和管理第三方服务内容的场景。
  • 通过 clawhub 安装并使用 openclaw skills install auth0-token-vault 命令部署。
  • 使用时不能将工具输出直接作为最终结论,涉及用户数据时应先确认最小权限和操作边界。
  • 建议结合来源仓库和原始 README 文档进一步核验具体用法和功能边界。

SKILL.md

name
auth0-token-vault
description
>
compatibility
Requires Node.js 18+ and auth0-tv installed globally (npm i -g auth0-token-vault-cli)
license
MIT
allowed-tools
Bash(auth0-tv *)
metadata
author
auth0
version
0.1
openclaw
emoji
\F510
requires
bins
os
install
kind
node
package
auth0-token-vault-cli
bins
[auth0-tv]
label
Install auth0-tv (npm)

Auth0 Token Vault CLI

Use the auth0-tv command-line tool to access third-party services on behalf of authenticated users via Auth0 Token Vault.

Current status

  • Auth status: !auth0-tv --json status 2>/dev/null || echo '{"error":{"code":"not_configured","message":"auth0-tv not configured or not logged in"}}'

When to use this skill

  • The user asks to read, search, send, reply, forward, archive, or delete emails
  • The user wants to manage email drafts or labels
  • The user wants to connect or disconnect a third-party service (Gmail, etc.)
  • The user asks about their authentication or connection status

Key patterns

Always use --json mode

All commands must use --json for structured output:

auth0-tv --json <command>

Alternatively, set AUTH0_TV_OUTPUT=json in the environment to avoid passing --json on every call.

Destructive actions require --confirm

Commands that modify data (send, delete, archive, forward, reply, draft send, draft delete) require --confirm:

auth0-tv --json --confirm gmail send --to user@example.com --subject "Subject" --body "Body"

Exit codes and recovery

CodeMeaningRecovery action
0SuccessParse JSON output
1General errorReport error to user
2Invalid inputCheck command syntax and required flags
3Auth requiredTell the user to run auth0-tv login
4Connection requiredTell the user to run auth0-tv connect <service>
5Service errorRetry or report upstream API failure
6Network errorCheck connectivity, retry

Important: Exit codes 3 and 4 require human intervention — login and connect open a browser for OAuth. Do not attempt to run these commands autonomously; instead, tell the user what to run.

Body input for email composition

For send, reply, and draft create, the message body can be provided via:

  • --body "inline text" — short messages
  • --body-file ./message.txt — longer messages from a file
  • stdin: echo "body" | auth0-tv --json --confirm gmail send --to ... --subject ...

Prefer --body-file or stdin for messages containing special characters.

Available commands

Authentication & setup

  • auth0-tv login — authenticate via browser (human-in-the-loop)
  • auth0-tv logout — clear stored credentials
  • auth0-tv status — show current user and connected services
  • auth0-tv connect <service> — connect a service via browser (human-in-the-loop)
  • auth0-tv disconnect <service> — disconnect a service
  • auth0-tv connections — list connected services

Gmail

  • auth0-tv gmail search <query> — search messages (supports Gmail search syntax)
  • auth0-tv gmail read <messageId> — read a message
  • auth0-tv gmail send — send a new message (destructive)
  • auth0-tv gmail reply <messageId> — reply to a message (destructive)
  • auth0-tv gmail forward <messageId> — forward a message (destructive)
  • auth0-tv gmail archive <messageId> — archive a message (destructive)
  • auth0-tv gmail delete <messageId> — move to trash (destructive)
  • auth0-tv gmail labels — list labels
  • auth0-tv gmail label <messageId> — add/remove labels
  • auth0-tv gmail draft create — create a draft
  • auth0-tv gmail draft list — list drafts
  • auth0-tv gmail draft send <draftId> — send a draft (destructive)
  • auth0-tv gmail draft delete <draftId> — delete a draft (destructive)

See references/commands.md for full command reference with flags and JSON output examples.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

96.19%
按下载量换算1,493

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills