什么是 Sentinel Shield？

Sentinel Shield 是一个轻量级安全层，专门设计用于保护 Openclaw Skills 的运行时环境。传统安全关注 LLM 本身，而该技能坚控智能体的实际操作，为防御信息窃取程序和未经授权的会话访问提供关键防线。它确保即使智能体遇到恶意指令，您的网关令牌和敏感系统文件也能受到保护。

通过在坚控层中包装智能体操作，Sentinel Shield 提供了对工具调用的深度可见性并实施严格的行为护栏。这种方法将标准自动化转变为加固的、生产就绪的智能体，能够在威胁导致数据外泄或系统损坏之前识别并缓解威胁。

下载入口:https://github.com/openclaw/skills/tree/main/skills/shadowfax-mitch/sentinel-shield

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Sentinel Shield 应用场景

• 保护网关令牌和存储的凭据免受未经授权的外泄尝试。
• 在智能体会话期间实时检测并阻止提示词注入模式。
• 通过自动速率限制和紧急切断开关防止失控的智能体循环。
• 坚控 SSH 密钥和密码文件等关键系统文件，防止未经授权的更改。
• 使用行为指纹识别审计智能体行为，以识别潜在的会话劫持。

1. 安全层通过为关键系统和配置文件建立加密基准进行初始化。
2. 它持续扫描入站文本，对比 16 种以上已知的注入模式特征，以防止恶意有效负载执行。
3. 滑动窗口速率限制器跟踪工具调用，执行每 60 秒 50 次调用的限制以停止失控进程。
4. 系统坚控宿主环境的文件完整性违规，特别关注 Openclaw Skills 使用的网关认证令牌。
5. 根据威胁级别，该技能会记录事件、发送实时 T@elegrimm 警报或执行紧急切断开关以终止会话。

Sentinel Shield 配置指南

要将 Sentinel Shield 与您的 Openclaw Skills 集成，请遵循以下安装步骤：

1. 初始化安全基准以保护您的配置文件：

node scripts/sentinel.js init

2. 在 {baseDir}/config/shield.json 中配置您的警报设置（T@elegrimm 机器人令牌和聊天 ID）。
3. 验证当前安全状态和活动会话统计数据：

node scripts/sentinel.js status

Sentinel Shield 数据架构与分类体系

Sentinel Shield 通过结构化配置和对 Openclaw Skills 必不可少的特定文件系统路径的实时坚控来管理安全数据。

name: sentinel-shield
description: Runtime security for OpenClaw agents. Monitors tool calls, enforces rate limits, scans for prompt injection, and alerts on suspicious behavior. Protect your gateway token and agent session from infostealers and session hijacking.
homepage: https://sentinel-algo.com/shield
triggers:
  - sentinel status
  - check security
  - security audit
  - recent alerts
  - sentinel shield
  - run security check
  - check for threats
  - agent security
metadata:
  emoji: "???"
  category: security
  tags:
    - security
    - monitoring
    - rate-limiting
    - injection-detection
    - audit-logging

Sentinel Shield — Runtime Security for OpenClaw Agents

Everyone else secures the model. We secure the agent.

Sentinel Shield is a lightweight security layer for OpenClaw agents. It monitors what your agent does — not just what it says — and alerts you before damage is done.

What It Protects Against

• Stolen gateway tokens — Rate limiting + anomaly detection catches unauthorized sessions
• Prompt injection — Scans inbound content for 16+ injection pattern signatures
• Session hijacking — Behavioral fingerprinting flags sessions that don't match your patterns
• Runaway agents — 50-call/60s sliding window kills runaway loops automatically
• Silent exfiltration — File integrity monitoring on critical OpenClaw files

Quick Commands

Status Check

node {baseDir}/scripts/sentinel.js status

Returns current health, active session stats, and recent alert summary.

Security Audit

node {baseDir}/scripts/sentinel.js audit

Full audit: file integrity, rate limit state, injection scanner status, anomaly log.

Recent Alerts

node {baseDir}/scripts/sentinel.js alerts [--hours 24]

Shows alerts from the last N hours (default: 24).

Rate Limit Status

node {baseDir}/scripts/sentinel.js ratelimit

Shows current call counts per window for all monitored tools.

Kill Switch

node {baseDir}/scripts/sentinel.js kill

Emergency stop. Terminates active rate counters, logs kill event, sends T@elegrimm alert.

Run Injection Scan

node {baseDir}/scripts/sentinel.js scan --text "some content to check"

Manually scan text for injection signatures.

Initialize / Reset Baselines

node {baseDir}/scripts/sentinel.js init

Establishes file integrity baselines for critical OpenClaw files.

Configuration

Edit {baseDir}/config/shield.json to customize:

{
  "rateLimit": {
    "maxCalls": 50,
    "windowSeconds": 60,
    "alertThreshold": 40
  },
  "telegram": {
    "enabled": true,
    "botToken": "YOUR_BOT_TOKEN",
    "ch@tId": "YOUR_CHAT_ID"
  },
  "monitoredFiles": [
    "~/.openclaw/openclaw.json",
    "~/.openclaw/credentials",
    "~/.ssh/authorized_keys",
    "/etc/passwd"
  ],
  "injectionScanning": true,
  "alertLevel": "medium"
}

Setup (T@elegrimm Alerts)

1. Create a T@elegrimm bot via @BotFather → copy the token
2. Message your bot to get your ch@t ID: https://api.telegram.org/bot/getUpdates
3. Add both to {baseDir}/config/shield.json

How to Use in Agent Sessions

When you see a suspicious message or want to verify your session is clean:

User: "Run a security check" Action: Run node {baseDir}/scripts/sentinel.js status

User: "Show me recent security alerts"
Action: Run node {baseDir}/scripts/sentinel.js alerts

User: "Scan this text for injection: [text]" Action: Run node {baseDir}/scripts/sentinel.js scan --text "[text]"

User: "Emergency stop sentinel" Action: Run node {baseDir}/scripts/sentinel.js kill

Alert Levels

Files Monitored (Default)

• ~/.openclaw/openclaw.json — Gateway auth token (THE critical file)
• ~/.openclaw/credentials — Stored credentials
• ~/.ssh/authorized_keys — SSH access control
• /etc/passwd — System user accounts
• /etc/sudoers — Privilege escalation paths

Version History

• v0.2.0 — Rate limiting (50/60s sliding window), T@elegrimm alerts, clawhub distribution
• v0.1.0 — File integrity monitoring, process scanning, injection detection (16 patterns)