这是关键的安全声明，且目前能够抵御智能体受损、提示注入、日志窃取和技能外泄。阅读 [docs/THREAT-MODEL.md](https://github.com/rohansx/wardn/blob/main/docs/THREAT-MODEL.md) 以了解已覆盖和未覆盖范围的诚实划分——包括在何种层级下可实现更强的“主机受损不会泄露任何信息”这一声明。

保险库本身（静态加密，基于口令派生的密钥）是一个真实组件，也是防火墙可以在单台机器上运行的原因。即将推出的 [docs/HOSTED-TIER.md](https://github.com/rohansx/wardn/blob/main/docs/HOSTED-TIER.md) 层级还将在代理周围包裹一个机密计算飞地，即使 VPS 被完全入侵，也无法读取密钥。

[![Crates.io](https://img.shields.io/crates/v/wardn.svg)](https://crates.io/crates/wardn)
[![License](https://img.shields.io/crates/l/wardn.svg)](LICENSE)

## 问题所在

如今，每个 AI 智能体框架都将 API 密钥存储在环境变量或 `.env` 文件中。一个受损的智能体、恶意技能、商品级窃密软件或提示注入，只要从 LLM 日志中提取出 `Authorization: Bearer sk-...`，就能完全获得你的凭证。```
~/.env              → OPENAI_KEY=sk-proj-real-key      # plaintext, readable by anyone
agent context       → "Use OPENAI_KEY=sk-proj-real-key" # leaked into LLM context window
agent logs          → Authorization: Bearer sk-proj-... # sitting in log files

## 架构```mermaid
flowchart TB
    subgraph Agent["AI Agent Process"]
        A1["Agent Code"]
        A2["ENV: OPENAI_KEY=wdn_placeholder_a1b2..."]
    end

    subgraph Wardn["wardn daemon · localhost:7777"]
        direction TB
        P["HTTP Proxy"]
        MCP["MCP Server\n(stdio)"]

        subgraph Pipeline["Request Pipeline"]
            direction LR
            S1["Identify\nAgent"] --> S2["Resolve\nPlaceholder"] --> S3["Check\nAuth"] --> S4["Rate\nLimit"] --> S5["Inject\nReal Key"]
        end

        subgraph ResponsePipeline["Response Pipeline"]
            direction RL
            R1["Strip Real\nKeys"] --> R2["Replace with\nPlaceholders"]
        end

        subgraph Vault["Encrypted Vault"]
            V1["AES-256-GCM"]
            V2["Argon2id KDF"]
            V3["Placeholder Map\nper agent × credential"]
        end
    end

    subgraph External["External APIs"]
        E1["api.openai.com"]
        E2["api.anthropic.com"]
        E3["..."]
    end

    A1 -- "placeholder token\nin headers/body" --> P
    A1 -. "MCP: get_credential_ref\nlist_credentials\ncheck_rate_limit" .-> MCP
    MCP -. "placeholder token\n(never real keys)" .-> A1
    P --> Pipeline
    Pipeline --> External
    External --> ResponsePipeline
    ResponsePipeline -- "response with\nplaceholders only" --> A1
    Pipeline <--> Vault
    ResponsePipeline <--> Vault

    style Agent fill:#1a1a2e,stroke:#e94560,color:#fff
    style Wardn fill:#0f3460,stroke:#16213e,color:#fff
    style Pipeline fill:#16213e,stroke:#e94560,color:#fff
    style ResponsePipeline fill:#16213e,stroke:#e94560,color:#fff
    style Vault fill:#1a1a2e,stroke:#00d2ff,color:#fff
    style External fill:#0a0a0a,stroke:#533483,color:#fff

## Demo

<p align="center">
  <img src="https://assets.kitploit.com/production/public/readmes/12823/1fa6109ffd855ec98c173c5edd2d7ee77f6b0c918a3cdecb1ea5fbfe8326161d.gif" alt="wardn demo" width="800">
</p>

## 信任级别（坦诚版）

| 层级 | 部署位置 | 保障内容 |
|---|---|---|
| **自托管（当前）** | 你的笔记本电脑、你的VPS、CI | 静态加密保险库、防火墙声明对抗代理。**不**防御主机上的root权限。 |
| **托管（即将推出）** | wardn管理或自带云 | 机密计算环境（Nitro / SEV-SNP） + 远程证明 + 加密到代理流程。真正实现'主机被攻破也不泄露任何信息'的声明。 |

自托管层级是当前的主力保障，现已发布。托管层级是严格升级路径：需要费用和运维复杂度，其设计见 [docs/HOSTED-TIER.md](https://github.com/rohansx/wardn/blob/main/docs/HOSTED-TIER.md)。以下是涵盖与未涵盖内容的完整坦诚清单：

👉 **[docs/THREAT-MODEL.md](https://github.com/rohansx/wardn/blob/main/docs/THREAT-MODEL.md)** — 涵盖/未涵盖表格，明确指出'任何软件保险库都无法消除主机被攻破的风险'，以及升级路径。

## 安装```bash
# Prebuilt binary (Linux/macOS, amd64/arm64), checksum-verified
curl -sSf https://raw.githubusercontent.com/rohansx/wardn/main/install.sh | sh

# or from crates.io
cargo install wardn

# or Homebrew, once the tap is published (see Formula/wardn.rb)
brew install rohansx/wardn/wardn

就这样。Claude Code 现在使用 wardn 的 MCP 服务器来获取占位符令牌，而不是从你的环境中读取真实密钥。

### 接下来会发生什么

1. Claude Code 调用 `get_credential_ref` → 获取 `wdn_placeholder_a1b2...`（非真实密钥）
2. 代理通过 wardn 代理发送包含占位符的请求
3. 代理将占位符替换为真实密钥，转发给 API
4. 代理在返回响应前从代理处剥离真实密钥

真实密钥永远不会进入代理的内存、日志或 LLM 上下文窗口。

## 本地仪表盘

一旦守护进程启动（`wardn serve` 或由 `wardn run` 生成），在浏览器中打开 **http://127.0.0.1:7777/ui**。它是一个只读、仅限本地的视图，包含：

- **凭证** — 每个存储的凭证及其 ACL（允许的代理、允许的域、速率限制 + 预算徽章）。
- **最近活动** — 最近 50 个代理事件，包括方法、域、路径、状态、代理、request_id 和记录的成本（`request_completed`、`credential_injected`、`rate_limit`、`budget_exceeded`、`loop_detected`、`request_error`）。
- **预算** — 每个凭证的配置预算（最大值、已花费、剩余、窗口、模式），并带有进度条，当超过 50%/80% 时从警告变为错误。

每 2 秒自动轮询。没有变更端点 —— 离开仪表盘的唯一途径是 API 本身（`/api/summary`、`/api/credentials`、`/api/audit?limit=N`、`/api/budgets`）。```bash
# Static, anonymous, never sees real keys
curl http://127.0.0.1:7777/api/summary | jq

## CLI 参考

### Vault 管理```bash
wardn vault create                        # create encrypted vault
wardn vault set OPENAI_KEY                # store credential (prompts for value, no echo)
wardn vault get OPENAI_KEY                # get placeholder token (never the real value)
wardn vault get OPENAI_KEY --agent bot    # get placeholder for specific agent
wardn vault list                          # list all credentials
wardn vault rotate OPENAI_KEY             # rotate value, placeholders unchanged
wardn vault remove OPENAI_KEY             # remove credential

# Custom vault path
wardn --vault /path/to/vault.enc vault list

### Claude Code / Cursor 集成```bash
wardn setup claude-code                   # register wardn as MCP server in Claude Code
wardn setup cursor                        # register wardn as MCP server in Cursor

# Or manually:
claude mcp add --transport stdio --scope user wardn -- wardn serve --mcp --agent claude-code

#### 可用的 MCP 工具

| 工具 | 返回内容 | 安全性 |
|------|----------------|----------|
| `get_credential_ref` | 占位符令牌 (`wdn_placeholder_...`) | 绝不是真实值 |
| `list_credentials` | 凭据名称 + 元数据 | 根据代理的访问权限过滤 |
| `check_rate_limit` | 剩余配额、重试信息 | 只读 |

### 凭据迁移```bash
wardn migrate --dry-run                             # audit Claude Code dir for exposed keys
wardn migrate --source claude-code                  # scan + migrate to vault
wardn migrate --source open-claw                    # scan OpenClaw config
wardn migrate --source directory --path ./my-proj   # scan any directory

每个导入器在首次使用时都会提示输入密码库密码（或从 `WARDN_PASSPHRASE` / 操作系统钥匙串读取）。现有的值会被静默覆盖——导入器仅处理值，元数据（允许的代理 / 域名 / 速率限制 / 预算）保持不变。

### 自动化

在 CI/脚本中，设置 `WARDN_PASSPHRASE` 和 `WARDN_VALUE` 环境变量以跳过交互提示：```bash
WARDN_PASSPHRASE=my-pass wardn vault list
WARDN_PASSPHRASE=my-pass WARDN_VALUE=sk-proj-xxx wardn vault set OPENAI_KEY

### 保险库操作```rust
use wardn::{Vault, config::CredentialConfig};

// Create an encrypted vault
let vault = Vault::create("vault.enc", "my-passphrase")?;

// Store a credential
vault.set_with_config("OPENAI_KEY", "sk-proj-real-key-123", &CredentialConfig {
    allowed_agents: vec!["researcher".into(), "writer".into()],
    allowed_domains: vec!["api.openai.com".into()],
    rate_limit: Some(RateLimitConfig { max_calls: 200, per: TimePeriod::Hour }),
})?;

// Agent gets a placeholder (not the real key)
let placeholder = vault.get_placeholder("OPENAI_KEY", "researcher")?;
// → "wdn_placeholder_a1b2c3d4e5f6g7h8"

// Rotate the real key — all placeholders keep working
vault.rotate("OPENAI_KEY", "sk-proj-new-key-456")?;

### MCP Server```rust
use wardn::mcp::WardenMcpServer;

// Serve over stdio (for Claude Code, Cursor, etc.)
WardenMcpServer::serve_stdio(vault, rate_limiter, "agent-id".into()).await?;

设置 `RUST_LOG=wardn=info`（或 `debug`/`trace`）以控制日志详细程度。日志输出到 stderr，从不输出到 stdout。

## 配置```toml
[warden]
vault_path = "~/.vibeguard/vault.enc"

[warden.credentials.OPENAI_KEY]
rate_limit = { max_calls = 200, per = "hour" }
allowed_agents = ["researcher", "writer"]
allowed_domains = ["api.openai.com"]

[warden.credentials.ANTHROPIC_KEY]
rate_limit = { max_calls = 100, per = "hour" }
allowed_agents = ["researcher"]
allowed_domains = ["api.anthropic.com"]

## 开发```bash
# Integration tests use a fast (insecure) KDF so the suite runs in
# milliseconds instead of paying the real Argon2id cost per test —
# always pass this feature flag when running tests locally or in CI:
cargo test --features test-fast-kdf

cargo build
cargo clippy --all-targets --features test-fast-kdf

subgraph KDF["Key Derivation"]
    Argon["Argon2id\nm=19456 t=2 p=1"]
end

subgraph Encrypt["Encryption"]
    AES["AES-256-GCM"]
    Nonce["Random Nonce\n(12 bytes)"]
end

subgraph Output["WDNV File"]
    direction TB
    Magic["WDNV (4B)"]
    Ver["Version (2B)"]
    SaltOut["Salt (16B)"]
    Payload["Nonce ‖ Ciphertext ‖ Tag"]
end

Pass --> Argon
Salt --> Argon
Argon -- "256-bit key" --> AES
Creds --> AES
Nonce --> AES
AES --> Payload

style Input fill:#1a1a2e,stroke:#e94560,color:#fff
style KDF fill:#16213e,stroke:#00d2ff,color:#fff
style Encrypt fill:#16213e,stroke:#00d2ff,color:#fff
style Output fill:#0f3460,stroke:#533483,color:#fff

### 文件格式```
Bytes 0-3:   Magic "WDNV"
Bytes 4-5:   Version (u16 LE)
Bytes 6-21:  Argon2id salt (16 bytes)
Bytes 22+:   AES-256-GCM encrypted payload (nonce ‖ ciphertext ‖ tag)