据 AlphaMoat 统计,截至 2026-09,Janee 累计下载 3,776 次、获 1 个星标,在全部 5,078 个 AI 技能中排名第 2,808 位,在「运维安全」分类(264 个)中排名第 173 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 120 | 3,611 | 1 | - |
| SkillHub ↗ | 150 | 3,776 | 1 | — |
各平台的计数口径不同,统计时间不一致。
主文声称 Janee 会加密保存密钥、在请求时注入凭据,并支持按路径配置策略、记录审计轨迹和撤销访问;还描述了 OpenClaw 插件集成。上述安全能力是源文中的产品主张,当前素材未独立验证。部署前应审查实现、密钥存储和访问策略,采用最小权限,并避免把敏感值放入聊天或日志;通过代理发起的请求仍可能产生外部副作用。 需 Node/npm 与兼容 MCP/插件。已报告 URL 处理缺陷可能泄漏存储凭据:拒绝绝对及协议相对路径,注入凭据前验证最终 origin,获批本地开发外强制 HTTPS。确认这些修复后才能使用生产或高权限密钥。
资料发布于 2026-10-27
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 3,776 | — | 1 |
| 2026-08 | 3,520 | +2.2% | 1 |
| 2026-07 | 3,445 | +7.6% | 1 |
| 2026-06 | 3,201 | +4.0% | 1 |
| 2026-05 | 3,078 | — | 1 |
| 2026-03 | 2,567 | — | 1 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
---
name: janee
version: 0.1.0
description: Secrets management for AI agents. Never expose your API keys again.
homepage: https://github.com/rsdouglas/janee
metadata: {"category": "security", "emoji": "🔐"}
---
# Janee
Secrets management for AI agents. Store API keys encrypted, make requests through Janee, never touch the real key.
## Why Use Janee?
Most skills tell you to store API keys in plaintext config files. One prompt injection, one leaked log, one compromised session — and your keys are exposed.
Janee fixes this:
- **Keys encrypted at rest** — not plaintext JSON
- **Agent never sees the real key** — requests go through Janee
- **Path-based policies** — restrict what endpoints can be called
- **Full audit trail** — every request logged
- **Kill switch** — revoke access without rotating keys
## Install
```bash
npm install -g @true-and-useful/janee
janee init
```
## Add a Service
```bash
janee add
```
Follow the prompts to add your API credentials. Keys are encrypted automatically.
## Use in Your Agent
Instead of calling APIs directly with your key, call them through Janee:
```bash
# Old way (dangerous):
curl -H "Authorization: Bearer sk_live_xxx" https://api.stripe.com/v1/balance
# Janee way (safe):
# Agent calls execute(capability, method, path) via MCP
# Janee injects the key, agent never sees it
```
## OpenClaw Integration
Install the OpenClaw plugin for native tool support:
```bash
openclaw plugins install @true-and-useful/janee-openclaw
```
Your agent now has:
- `janee_list_services` — see available APIs
- `janee_execute` — make requests through Janee
- `janee_reload_config` — hot-reload after config changes
## Example: Secure Moltbook Access
Instead of storing your Moltbook key in `~/.config/moltbook/credentials.json`:
```bash
janee add moltbook -u https://www.moltbook.com/api/v1 -k YOUR_KEY
```
Then use Janee to post:
```yaml
# Your agent calls:
janee_execute(service="moltbook", method="POST", path="/posts", body=...)
```
Your Moltbook key stays encrypted. Even if your agent is compromised, the key can't be exfiltrated.
## Config Example
```yaml
services:
stripe:
baseUrl: https://api.stripe.com
auth:
type: bearer
key: sk_live_xxx # encrypted
moltbook:
baseUrl: https://www.moltbook.com/api/v1
auth:
type: bearer
key: moltbook_sk_xxx # encrypted
capabilities:
stripe_readonly:
service: stripe
rules:
allow: [GET *]
deny: [POST *, DELETE *]
moltbook:
service: moltbook
ttl: 1h
autoApprove: true
```
## Architecture
```
┌─────────────┐ ┌──────────┐ ┌─────────┐
│ AI Agent │─────▶│ Janee │─────▶│ API │
│ │ MCP │ │ HTTP │ │
└─────────────┘ └──────────┘ └─────────┘
│ │
No key Injects key
+ logs request
```
## Links
- GitHub: https://github.com/rsdouglas/janee
- npm: https://www.npmjs.com/package/@true-and-useful/janee
- OpenClaw Plugin: https://www.npmjs.com/package/@true-and-useful/janee-openclaw
在使用技能包之前做安全扫描,并按结论决定放行或拦截的技能。
管理OpenClaw的OpenRouter免费AI模型,自动按质量排名模型,配置速率限制备用方案,并更新opencla...
备份与恢复 OpenClaw 配置、凭据与工作区的技能。
配置并使用 1Password CLI 处理密钥。
一款被描述为可检测提示注入与危险命令的 OpenClaw 安全插件。
远程控制 tmux 会话,向交互式命令行发送按键并抓取输出。
以应用安全工程师视角做代码与架构的安全审计。
管理腾讯云对象存储与数据万象的技能。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。