首页龙虾技能列表 › proxy-web-fetch

proxy-web-fetch

v1.0.0

Proxy Web Page Fetch Tool - Fetches and parses web page content into structured Markdown or text via the OpenClaw Manager proxy. Use when: - Need to fetch an...

0· 245·1 当前·1 累计
by @whyhit2005·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/14
安全扫描
VirusTotal
无害
查看报告
OpenClaw
可疑
medium confidence
The skill's functionality (posting a URL to a manager proxy and returning parsed content) is coherent, but there is an internal inconsistency about required environment variables and you must trust the configured proxy because it will receive arbitrary URLs and their content.
评估建议
Before installing: (1) Confirm the skill actually requires WEB_FETCH_PROXY_URL — the package metadata contradicts SKILL.md; ask the author to update metadata if needed. (2) Only set WEB_FETCH_PROXY_URL to a proxy you fully trust (the proxy will receive every URL you ask it to fetch and can fetch internal resources). (3) If you allow autonomous agent runs, consider restricting what URLs the agent may request or disable autonomous invocation for this skill. (4) Because source and homepage are unkn...
详细分析 ▾
用途与能力
The skill's name, description, script, and SKILL.md align: it uses curl to POST a URL to a Web Fetch Proxy and returns parsed Markdown/text. However the registry metadata at the top lists no required environment variables while SKILL.md and scripts require WEB_FETCH_PROXY_URL — this mismatch is an incoherence that should be clarified before install.
指令范围
Runtime instructions and the included script are narrowly scoped: they build a JSON payload with the requested URL and options and POST it to the proxy. The skill does not read other files, system paths, or unrelated env vars. Note: because the proxy will fetch the provided URLs, the operator of the proxy can see or fetch arbitrary targets (including internal network addresses) — that risk is inherent to the stated purpose.
安装机制
This is an instruction-only skill with a small shell wrapper included; there is no install spec or external downloads. The only required binary is curl, which is reasonable and proportionate.
凭证需求
The script requires a single env var, WEB_FETCH_PROXY_URL, which is proportionate to the purpose. The inconsistency between the registry 'Required env vars: none' and the SKILL.md that declares WEB_FETCH_PROXY_URL required is a meaningful mismatch and should be corrected. Also, the skill delegates API key management to the manager proxy — you must trust that manager's secret handling.
持久化与权限
The skill does not request persistent or elevated system privileges and does not set always:true. Autonomous invocation is allowed (default) which is normal for skills; if you enable autonomous use, be aware an agent could request arbitrary URLs via the proxy — consider limiting agent autonomy or URL allowlists if available.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/3/14

Initial release of the Proxy Web Page Fetch Tool. - Fetches and parses web page content to Markdown or plain text via the OpenClaw Manager proxy. - Supports options for caching, image retention, page summaries, and metadata extraction. - No manual API key configuration needed; authentication handled internally by the Manager. - Configurable via the required `WEB_FETCH_PROXY_URL` environment variable. - Includes a handy shell script for command-line usage and various fetch scenarios.

● 无害

安装命令 点击复制

官方npx clawhub@latest install proxy-web-fetch
镜像加速npx clawhub@latest install proxy-web-fetch --registry https://cn.clawhub-mirror.com

技能文档

Fetch and parse web page content via the OpenClaw Manager Web Fetch Proxy. The Manager handles API key injection from encrypted storage automatically — no manual key configuration needed.

The proxy URL is configured via the WEB_FETCH_PROXY_URL environment variable (required). If not set, the skill will not be available.

Quick Start

Basic cURL Usage

curl --request POST \
  --url "${WEB_FETCH_PROXY_URL}/" \
  --header 'Content-Type: application/json' \
  --data '{
    "url": "https://www.example.com"
  }'

Script Usage

A wrapper shell script is provided for convenience.

# Basic Fetch (returns Markdown by default)
./scripts/proxy_fetch.sh --url "https://www.example.com"

# Fetch as plain text, no cache ./scripts/proxy_fetch.sh \ --url "https://docs.python.org/3/" \ --format text \ --no-cache

# Fetch with image and link summaries ./scripts/proxy_fetch.sh \ --url "https://news.example.com/article" \ --images-summary \ --links-summary

# Fetch without images, disable GFM ./scripts/proxy_fetch.sh \ --url "https://blog.example.com/post" \ --no-images \ --no-gfm

Authentication

No authentication required — the proxy reads API keys internally from the Manager's encrypted secrets store.

API Parameter Reference

ParameterTypeRequiredDefaultDescription
urlstring-URL of the web page to fetch
timeoutinteger-20Request timeout in seconds
no_cacheboolean-falseDisable caching (true/false)
return_formatstring-markdownReturn format: markdown or text
retain_imagesboolean-trueRetain images in output (true/false)
no_gfmboolean-falseDisable GitHub Flavored Markdown (true/false)
keep_img_data_urlboolean-falseKeep image data URLs (true/false)
with_images_summaryboolean-falseInclude images summary (true/false)
with_links_summaryboolean-falseInclude links summary (true/false)

Response Structure

The proxy returns JSON with the parsed page content.

{
  "id": "task-id",
  "created": 1704067200,
  "request_id": "request-id",
  "model": "model-name",
  "reader_result": {
    "title": "Page Title",
    "description": "Brief page description",
    "url": "https://www.example.com",
    "content": "Parsed page content (Markdown or text)",
    "external": {
      "stylesheet": {}
    },
    "metadata": {
      "keywords": "page, keywords",
      "viewport": "width=device-width",
      "description": "Meta description",
      "format-detection": "telephone=no"
    }
  }
}

Key Response Fields

FieldDescription
reader_result.contentMain parsed content (body text, images, links)
reader_result.titlePage title
reader_result.descriptionBrief page description
reader_result.urlOriginal page URL
reader_result.metadataPage metadata (keywords, viewport, etc.)

Common Use Cases

ScenarioCommand
Read a documentation page--url
Extract text only (no images)--url --no-images --format text
Force fresh fetch (bypass cache)--url --no-cache
Get content with all summaries--url --images-summary --links-summary
Long page with extended timeout--url --timeout 60

Environment Requirements

  • OpenClaw Manager must be running with the Web Fetch Proxy enabled.
  • WEB_FETCH_PROXY_URL environment variable must be set to the proxy URL (required, no default).
  • curl command must be available in your system path.
数据来源:ClawHub ↗ · 中文优化:龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险,如需更匹配、更安全的方案,建议联系付费定制

了解定制服务