Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计提醒

oauth-disguiseOAuth disguise 安全

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

7,089

周安装

284

GitHub Stars

公开资料未说明

下载量

2,295
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:oauth-disguise(OAuth disguise 安全)
来源仓库:https://github.com/jiafar/oauth-disguise
安装命令:
openclaw skills install oauth-disguise
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 oauth-disguise

简介

通过环境变量注入将 Anthropic OAuth 令牌 (sk-ant-oat01-*) 配置为 OpenClaw 中的 API 密钥,从而启用 Claude Pro/Team API 访问。

SKILL.md

name
oauth-disguise
version
1.1.0
description
Configure Anthropic OAuth tokens (sk-ant-oat01-*) to work with OpenClaw as API keys via environment variable injection. Use when: (1) user has OAuth tokens that fail direct API calls with authentication_error, (2) switching from proxy to Anthropic official API, (3) configuring Claude Pro/Team subscription tokens for API use. NOT for: standard API keys (sk-ant-api03-*), working proxy services, or non-Anthropic providers.

OAuth Token Disguise

Configure Anthropic OAuth tokens (sk-ant-oat01-*) as working API keys through OpenClaw's env.vars injection.

Core Method

Inject token via environment variable, reference with ${VAR} in provider config:

openclaw config patch '{
  "env": {
    "vars": {
      "ANTHROPIC_API_KEY": "sk-ant-oat01-YOUR_TOKEN"
    }
  },
  "models": {
    "providers": {
      "anthropic-official": {
        "baseUrl": "https://api.anthropic.com",
        "apiKey": "${ANTHROPIC_API_KEY}",
        "api": "anthropic-messages",
        "models": [
          {"id": "claude-sonnet-4-20250514", "name": "Claude Sonnet 4"},
          {"id": "claude-opus-4-6", "name": "Claude Opus 4.6"}
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "anthropic-official/claude-sonnet-4-20250514"
      }
    }
  }
}'

Then restart: openclaw gateway restart

Per-Agent Configuration

Apply to a single agent (keep others on proxy):

openclaw config patch '{
  "agents": {
    "list": [{
      "id": "YOUR_AGENT_ID",
      "name": "Agent Name",
      "workspace": "/path/to/workspace",
      "model": {"primary": "anthropic-official/claude-opus-4-6"}
    }]
  }
}'

Verification

Run session_status or openclaw status. Look for:

  • 🧠 Model: anthropic-official/* → ✅ success
  • custom-proxy/* or fallback notice → ❌ token invalid or auth cooldown

Troubleshooting

SymptomCauseFix
Still shows custom-proxy/*defaults.model.primary wrongSet to anthropic-official/MODEL_ID
Fallback after token switchAuth cooldown from rapid switchingWait 5 min, restart gateway
env variable missingGateway not restartedopenclaw gateway restart
Works then stopsToken expiredReplace token in env.vars, restart

Critical: Do not rapidly switch between tokens. OpenClaw tracks auth failures and applies cooldown periods. If stuck in fallback, use session_status with model parameter to force reset:

/model anthropic-official/claude-opus-4-6

Dual Provider Setup

Keep proxy as fallback while using official API:

{
  "env": {"vars": {"ANTHROPIC_API_KEY": "sk-ant-oat01-xxx"}},
  "models": {
    "providers": {
      "custom-proxy": {
        "baseUrl": "https://your-proxy.com/",
        "apiKey": "proxy-key",
        "api": "anthropic-messages",
        "models": [{"id": "claude-sonnet-4-5", "name": "Claude Sonnet 4.5"}]
      },
      "anthropic-official": {
        "baseUrl": "https://api.anthropic.com",
        "apiKey": "${ANTHROPIC_API_KEY}",
        "api": "anthropic-messages",
        "models": [
          {"id": "claude-sonnet-4-20250514", "name": "Claude Sonnet 4"},
          {"id": "claude-opus-4-6", "name": "Claude Opus 4.6"}
        ]
      }
    }
  }
}

Security

  • Tokens auto-redacted in config.get output (__OPENCLAW_REDACTED__)
  • Direct curl with these tokens fails (only works through OpenClaw)
  • Never commit openclaw.json with raw tokens to version control
  • Use env.vars (not inline apiKey) to keep tokens in one place

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

80.67%
按下载量换算1,851

安全审计

VirusTotal

未展示

ClawScan

可疑

Static analysis

通过

权限和风险

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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