← 返回 Skills 市场
yangzhe1991

Find RSS

作者 Zhe (Phil) Yang · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
357
总下载
1
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install find-rss
功能描述
Discover RSS and Atom feeds for any website. Use when the user wants to find RSS feeds, subscribe to website updates, or locate syndication feeds for news ag...
使用说明 (SKILL.md)

Find RSS Skill

Discover RSS and Atom feeds for websites to enable news aggregation and content monitoring.

Quick Start

Run the find-rss script with a website URL:

~/.openclaw/skills/find-rss/scripts/find-rss.sh \x3Cwebsite_url>

Example:

~/.openclaw/skills/find-rss/scripts/find-rss.sh https://techcrunch.com/

What This Skill Does

  1. Checks HTML link tags - Searches for \x3Clink rel="alternate" type="application/rss+xml"> tags
  2. Tests common RSS paths - Tries standard feed locations like /feed, /rss, /atom
  3. Validates feeds - Confirms discovered URLs return valid RSS/Atom content

How It Works

The script performs two main checks:

1. HTML Link Tag Discovery

Most websites with RSS feeds include a link tag in their HTML:

\x3Clink rel="alternate" type="application/rss+xml" href="https://example.com/feed/">

The script extracts all such links from the page source.

2. Common Path Testing

If no link tags are found, the script tests common RSS paths:

  • /feed and /feed/
  • /rss and /rss/
  • /atom and /atom/
  • /index.xml, /feed.xml, /rss.xml
  • /blog/feed, /news/feed

Interpreting Results

  • ✅ Found in HTML: RSS link was discovered in the page's HTML source
  • ✅ Common path: RSS feed exists at a standard location
  • ❌ Not found: No RSS feed detected (website may not offer one)

Tips for Users

If no RSS feed is found:

  1. Check the website's footer for an "RSS" or "Subscribe" link
  2. Search Google for "[sitename] RSS feed"
  3. Use feed discovery services like Feedly or Inoreader
  4. Some sites use JSON Feeds or proprietary APIs instead of RSS

Common RSS Feed Patterns

Platform Typical Feed URL
WordPress https://site.com/feed/
Medium https://medium.com/feed/@username
Substack https://newsletter.substack.com/feed
Ghost https://site.com/rss/
YouTube https://www.youtube.com/feeds/videos.xml?channel_id=...

Limitations

  • Some websites block automated requests (may return 403)
  • JavaScript-rendered sites may hide RSS links
  • Relative URLs are resolved but may not always be accurate
  • Rate limiting may apply for multiple rapid requests
安全使用建议
This skill appears to do exactly what it says: a local shell script fetches the given URL and checks HTML and common paths for RSS/Atom feeds. Before installing, verify you are comfortable with the skill running curl/grep/sed on URLs you provide (these tools are not listed as required but are used by the script). Do not give it internal or sensitive network addresses if the agent has access to your internal network (it will attempt arbitrary HTTP requests and could be used to probe internal hosts). If you want extra caution: inspect the script yourself, run it in a sandbox or limited environment, and consider disabling autonomous invocation or restricting the skill so it only runs on user confirmation.
功能分析
Type: OpenClaw Skill Name: find-rss Version: 1.0.0 The skill is designed to discover RSS feeds but contains a potential argument injection vulnerability in `scripts/find-rss.sh`. The script passes the user-provided URL directly to `curl` without sufficient sanitization, which could allow an attacker to inject additional flags (e.g., `-o` to overwrite files). While the behavior aligns with the stated purpose, the lack of input validation qualifies as a vulnerability under the provided criteria.
能力评估
Purpose & Capability
The name/description match the included behavior: the SKILL.md and scripts/search logic both implement feed discovery. One minor mismatch: the skill declares no required binaries, but the script relies on standard CLI tools (curl, grep, sed, sort, head). This is expected for a shell script but should have been declared.
Instruction Scope
The SKILL.md and script stay within scope: they fetch a provided URL, parse HTML for <link> tags, and probe common feed paths. The instructions do not read unrelated files, request secrets, or send discovered data to third parties. Note: the script will perform arbitrary HTTP(S) requests for whatever URL is given, so it can be used to probe internal or restricted hosts if run in an environment with such network access (SSRF-style risk).
Install Mechanism
No install spec; this is an instruction-only skill with a small shell script included. Nothing is downloaded from external sources or written to unusual locations during installation.
Credentials
The skill requests no environment variables, keys, or credentials. The script uses only the provided URL and makes network calls to that target; no secret access is required or requested.
Persistence & Privilege
always is false and the skill does not modify other skills or system configuration. It does not request persistent privileges or self-enable behavior beyond normal autonomous invocation (which is the platform default).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install find-rss
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /find-rss 触发
  4. 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: Discover RSS and Atom feeds for any website
元数据
Slug find-rss
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

Find RSS 是什么?

Discover RSS and Atom feeds for any website. Use when the user wants to find RSS feeds, subscribe to website updates, or locate syndication feeds for news ag... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 357 次。

如何安装 Find RSS?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install find-rss」即可一键安装,无需额外配置。

Find RSS 是免费的吗?

是的,Find RSS 完全免费(开源免费),可自由下载、安装和使用。

Find RSS 支持哪些平台?

Find RSS 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 Find RSS?

由 Zhe (Phil) Yang(@yangzhe1991)开发并维护,当前版本 v1.0.0。

💬 留言讨论