agent-safety

自主人工智能代理的出站安全——在输出离开机器之前对其进行扫描。 Git 预提交挂钩会自动阻止包含 API 密钥、令牌、PII 或机密的提交。与入站扫描仪（Skillvet、IronClaw）不同，这可以防止您意外发布的内容。在提交到 git 存储库、发布到 GitHub 或运行定期系统运行状况检查时使用。在 git 级别自动执行——而不是提示。

# Agent Safety

Automated safety tools for autonomous AI agents. The principle: **don't rely on prompts for safety — automate enforcement.**

All scripts are in this skill's `scripts/` directory. When OpenClaw loads this skill, resolve paths relative to this file's location.

## Pre-Publish Security Scan

Scans files for secrets, PII, and internal paths before publishing.

```bash
bash scripts/pre-publish-scan.sh <file-or-directory>
```

**Detects:**
- API keys (AWS, GitHub, Anthropic, OpenAI, generic patterns)
- Private keys (PEM blocks), Bearer tokens, hardcoded passwords
- Email addresses, phone numbers, SSNs, credit card patterns
- Physical addresses, name fields
- Home directory paths, internal config paths

**Exit 0** = clean. **Exit 1** = blocking issues found, do not publish.

## Git Pre-Commit Hook

Install once per repo. Automatically scans staged files on every commit:

```bash
bash scripts/install-hook.sh <repo-path>
```

- Scans staged content (what's being committed, not working tree)
- Blocks commit if secrets or SSNs found
- Flags PII for review
- Only bypassed with explicit `git commit --no-verify`

**Install this on every repo you work with.** It's the real guardrail.

## Health Check

System monitoring for disk, workspace, security, and updates:

```bash
bash scripts/health-check.sh
```

**Checks:** Disk usage, workspace size, memory file growth, OpenClaw version, macOS updates, firewall status, SIP status.

Run periodically (every few heartbeats). Watch for warnings.

## Rules

1. Run pre-publish scan before ANY external publish action
2. Install pre-commit hook on EVERY repo you work with
3. Blocking issues (secrets, SSNs) must be fixed — no override
4. Review items (emails, paths) need human judgment
5. If a secret was ever committed, it's compromised — rotate immediately

---

## 中文说明

# Agent Safety

面向自主 AI 代理的自动化安全工具。核心原则：**不要依赖提示词来保障安全——把强制执行自动化。**

所有脚本都位于本技能的 `scripts/` 目录中。当 OpenClaw 加载该技能时，请相对于本文件所在位置解析路径。

## 发布前安全扫描

在发布前扫描文件中的密钥、PII 和内部路径。

```bash
bash scripts/pre-publish-scan.sh <file-or-directory>
```

**检测内容：**
- API 密钥（AWS、GitHub、Anthropic、OpenAI 以及通用模式）
- 私钥（PEM 块）、Bearer 令牌、硬编码密码
- 电子邮件地址、电话号码、社会安全号码（SSN）、信用卡模式
- 实际地址、姓名字段
- 主目录路径、内部配置路径

**Exit 0** = 干净。**Exit 1** = 发现阻断性问题，请勿发布。

## Git 预提交挂钩

每个仓库安装一次。在每次提交时自动扫描暂存文件：

```bash
bash scripts/install-hook.sh <repo-path>
```

- 扫描暂存内容（即将被提交的内容，而非工作树）
- 若发现密钥或 SSN 则阻止提交
- 标记 PII 以供审查
- 仅在显式使用 `git commit --no-verify` 时绕过

**请在你接触的每一个仓库上都安装它。** 它才是真正的防护栏。

## 健康检查

针对磁盘、工作区、安全性和更新的系统监控：

```bash
bash scripts/health-check.sh
```

**检查项：** 磁盘占用、工作区大小、记忆文件增长、OpenClaw 版本、macOS 更新、防火墙状态、SIP 状态。

定期运行（每隔几次心跳）。留意警告。

## 规则

1. 在执行任何对外发布操作前运行发布前扫描
2. 在你接触的每一个仓库上安装预提交挂钩
3. 阻断性问题（密钥、SSN）必须修复——不可覆盖
4. 需审查的条目（电子邮件、路径）需要人工判断
5. 一旦某个密钥曾被提交，就视为已泄露——立即轮换