← 返回 Skills 市场
190
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install fetch-url
功能描述
Fetch raw HTTP response bodies from one or more URLs with optional custom headers and timeout, supporting JSON, XML, RSS, CSV, plain text, and files.
使用说明 (SKILL.md)
Fetch URL
Fetch raw HTTP responses from URLs. Supports multiple URLs and custom headers.
Usage
# Single URL
node {baseDir}/scripts/fetch.mjs "https://api.example.com/data"
# Multiple URLs
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/data1", "https://api.example.com/data2"]'
# With custom headers (per-URL)
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/json", "https://api.example.com/text"]' '[{"accept":"application/json"}, {"accept":"text/plain"}]'
# With timeout
node {baseDir}/scripts/fetch.mjs "https://api.example.com/data" --timeout 60000
Examples
JSON API
# GitHub API - get repository info
node {baseDir}/scripts/fetch.mjs "https://api.github.com/repos/microsoft/vscode" '{"accept":"application/json","user-agent":"Mozilla/5.0"}'
XML
# SOAP service or XML endpoint
node {baseDir}/scripts/fetch.mjs "https://api.example.com/soap" '{"accept":"application/xml"}'
# Sitemap
node {baseDir}/scripts/fetch.mjs "https://example.com/sitemap.xml"
RSS / Atom Feed
# RSS 2.0 feed
node {baseDir}/scripts/fetch.mjs "https://example.com/rss.xml" '{"accept":"application/rss+xml"}'
# Atom feed
node {baseDir}/scripts/fetch.mjs "https://example.com/atom.xml" '{"accept":"application/atom+xml"}'
CSV / Plain Text
# CSV data
node {baseDir}/scripts/fetch.mjs "https://example.com/data.csv" '{"accept":"text/csv"}'
# Plain text
node {baseDir}/scripts/fetch.mjs "https://example.com/robots.txt" '{"accept":"text/plain"}'
Multiple Formats
# Fetch JSON and XML in parallel
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/data.json", "https://api.example.com/data.xml"]' '[{"accept":"application/json"}, {"accept":"application/xml"}]'
Options
urls_json: JSON array of URLs or a single URL stringheaders_json: Optional JSON array of headers objects (same length as urls)--timeout \x3Cms>: Request timeout in milliseconds (default: 30000)
Notes:
- Returns raw HTTP response body
- For multiple URLs, returns JSON array of results
- Node.js 18+ required (native fetch)
安全使用建议
This skill appears to do what it says (fetch HTTP responses). Before installing: ensure the runtime provides Node.js 18+ and that the dependency (user-agents) is installed or vendored, because there is no install step included; verify the registry metadata correctly lists 'node' as a required binary. Most importantly, treat input URLs as sensitive: the skill will fetch arbitrary targets you pass it — avoid giving untrusted inputs that could point to internal services (localhost, cloud metadata endpoints such as 169.254.169.254) or file:// URLs. If you plan to enable autonomous invocation, consider restricting which hosts/paths the skill is allowed to fetch or requiring user confirmation for remote URLs to reduce SSRF/data-exfiltration risk.
功能分析
Type: OpenClaw Skill
Name: fetch-url
Version: 1.0.0
The skill is a standard HTTP client utility designed to fetch raw content (JSON, XML, etc.) from URLs. The implementation in `scripts/fetch.mjs` uses native Node.js fetch, supports custom headers, and includes a legitimate dependency (`user-agents`) to rotate User-Agent strings. No evidence of data exfiltration, malicious execution, or prompt injection was found; the code's behavior is entirely consistent with its documented purpose.
能力评估
Purpose & Capability
The name/description match the included script: the skill fetches raw HTTP responses for one or more URLs with optional per-URL headers and timeout. Minor mismatch: SKILL.md metadata declares 'node' as a required binary, but the registry metadata lists no required binaries; package.json declares a dependency (user-agents) so Node.js and dependencies are required at runtime.
Instruction Scope
SKILL.md instructs the agent to run the included Node script which only performs network fetches and prints results. The instructions and script do not read environment variables or local files. However, the skill will fetch arbitrary URLs provided by the caller — that means it can access internal endpoints (localhost/169.254.169.254, internal APIs) and return their contents. This is expected for a fetch tool but is a privacy/SSRF risk if untrusted inputs are allowed.
Install Mechanism
There is no install spec (instruction-only), which is low risk, but the package.json/package-lock indicate an npm dependency (user-agents). No install step is provided to install node_modules; the runtime therefore requires Node.js 18+ and that dependencies be available in the environment. This operational gap (no declared required binary in registry, no install step) may cause runtime failures or lead integrators to install dependencies manually.
Credentials
The skill requests no environment variables, no credentials, and does not access config paths. That is proportionate to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent system or agent-wide modifications. It does not modify other skills or system configuration.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install fetch-url - 安装完成后，直接呼叫该 Skill 的名称或使用
/fetch-url触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of the fetch-url skill.
- Fetches raw HTTP responses from URLs, supporting JSON, XML, RSS/Atom, CSV, plain text, files, and downloads.
- Allows fetching from multiple URLs in parallel and supports custom headers per URL.
- Supports request timeout configuration.
- Designed for non-HTML content; for HTML-to-markdown conversion, use fetch-webpage.
元数据
常见问题
Fetch Url 是什么？
Fetch raw HTTP response bodies from one or more URLs with optional custom headers and timeout, supporting JSON, XML, RSS, CSV, plain text, and files. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 190 次。
如何安装 Fetch Url？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install fetch-url」即可一键安装，无需额外配置。
Fetch Url 是免费的吗？
是的，Fetch Url 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Fetch Url 支持哪些平台？
Fetch Url 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Fetch Url？
由 长安（@roaycl）开发并维护，当前版本 v1.0.0。
推荐 Skills