dojo.md
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
安全的智能网页抓取技能,节省 50-80% Token。替代内置 web_fetch,自动使用 Jina Reader 清洗服务获取干净 Markdown。内置 URL 白名单验证、SSL 强制验证、敏感数据检测,防止 SSRF 和数据泄露。
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install bg1avd/safe-web-fetch-for-save-tokenInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
安全的智能网页内容获取技能。保留原版的核心功能(Token 节省 50-80%),但增加多层安全防护。
# 获取清洗后的 Markdown
python3 {baseDir}/scripts/safe_fetch.py "https://example.com/article"
# JSON 格式输出(包含元信息)
python3 {baseDir}/scripts/safe_fetch.py "https://example.com/article" --json
# 查看安全配置
python3 {baseDir}/scripts/safe_fetch.py --show-config
当用户需要获取网页内容时:
用户: "帮我查一下 https://example.com/article 的内容"
Agent 应该:
1. 运行: python3 ~/.openclaw/skills/safe-web-fetch/scripts/safe_fetch.py "https://example.com/article"
2. 获得清洗后的 Markdown 内容
阻止以下危险 URL:
发送前检测页面内容,拒绝发送包含:
api_key=, apikey=, key=)access_token=, token=)Bearer , Authorization: )AKIA, aws_)-----BEGIN.*PRIVATE KEY-----)不会禁用 SSL 证书验证,确保:
在 config.json 中配置:
{
"allowed_domains": ["example.com", "docs.example.com"],
"blocked_domains": ["ads.example.com"],
"max_content_size": 10485760,
"timeout": 30
}
{
"success": true,
"url": "https://r.jina.ai/http://example.com/article",
"original_url": "https://example.com/article",
"content": "# Article Title\n\nClean markdown content...
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# Safe Web Fetch
安全的智能网页内容获取技能。保留原版的核心功能(Token 节省 50-80%),但增加多层安全防护。
## 核心功能
- **智能清洗**: 自动使用 Jina Reader 获取干净 Markdown
- **Token 优化**: 去除广告、导航栏等噪音,节省 50-80% Token
- **安全防护**:
- ✅ 强制 SSL 验证(不跳过)
- ✅ URL 白名单验证(阻止内网/私有 IP)
- ✅ 敏感数据检测(不发送包含 API Key/Token 的页面)
- ✅ 可配置允许列表
## 使用方式
### 基本用法
```bash
# 获取清洗后的 Markdown
python3 {baseDir}/scripts/safe_fetch.py "https://example.com/article"
# JSON 格式输出(包含元信息)
python3 {baseDir}/scripts/safe_fetch.py "https://example.com/article" --json
# 查看安全配置
python3 {baseDir}/scripts/safe_fetch.py --show-config
```
### 在 Agent 中使用
当用户需要获取网页内容时:
```
用户: "帮我查一下 https://example.com/article 的内容"
Agent 应该:
1. 运行: python3 ~/.openclaw/skills/safe-web-fetch/scripts/safe_fetch.py "https://example.com/article"
2. 获得清洗后的 Markdown 内容
```
## 安全特性
### 1. URL 白名单验证
阻止以下危险 URL:
- 私有 IP 地址(127.0.0.1, 192.168.x.x, 10.x.x.x, 172.16-31.x.x)
- localhost, *.local
- 内部域名(*.internal, *.localdomain)
- file://, ftp://, data:// 等非 HTTP 协议
### 2. 敏感数据检测
发送前检测页面内容,拒绝发送包含:
- API Keys(`api_key=`, `apikey=`, `key=`)
- Access Tokens(`access_token=`, `token=`)
- Bearer Tokens(`Bearer `, `Authorization: `)
- AWS Keys(`AKIA`, `aws_`)
- Private Keys(`-----BEGIN.*PRIVATE KEY-----`)
### 3. 强制 SSL 验证
不会禁用 SSL 证书验证,确保:
- 连接真实的服务器
- 防止中间人攻击
- 证书错误时拒绝连接
### 4. 可配置允许列表
在 `config.json` 中配置:
```json
{
"allowed_domains": ["example.com", "docs.example.com"],
"blocked_domains": ["ads.example.com"],
"max_content_size": 10485760,
"timeout": 30
}
```
## 输出格式
```json
{
"success": true,
"url": "https://r.jina.ai/http://example.com/article",
"original_url": "https://example.com/article",
"content": "# Article Title\n\nClean markdown content...University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
A股分析技能
A2A4B2B Skill for OpenClaw