by 安全扫描
OpenClaw
安全
high confidenceThe skill's code, instructions, and requirements match its stated purpose (fetch RSS / crawl pages and summarize); nothing requested or installed is disproportionate or unrelated.
评估建议
This skill appears coherent and does what it says: fetch RSS feeds or web pages and produce text the agent can summarize. Before installing or running it, consider: 1) The scripts will fetch any URL you or the agent supplies — avoid pointing it at internal services or private endpoints (risk of exposing internal data). 2) The fetched article text will be sent to your agent/LLM for summarization, so don't feed paywalled or confidential pages unless you accept that exposure. 3) Review rate limitin...详细分析 ▾
✓ 用途与能力
Name/description align with the provided artifacts: scripts/rss_fetcher.py fetches RSS feeds and scripts/crawl.py fetches and extracts page text. The SKILL.md describes using an LLM to summarize (LLM calls are expected to be performed by the agent, not the shipped scripts), which is consistent with an instruction-only skill.
ℹ 指令范围
Runtime instructions only tell the agent to run the included Python scripts and then use an LLM to summarize results. The scripts fetch arbitrary user-supplied URLs (no host whitelisting), so while this is expected for a crawler, it means the agent could be used to fetch internal/private endpoints or other sensitive URLs if directed to — the SKILL.md does advise respecting robots.txt and rate limits.
✓ 安装机制
No install spec is provided (instruction-only plus included Python scripts). Nothing is downloaded from external URLs or added to disk by an installer, so install risk is low.
✓ 凭证需求
The skill declares no required environment variables, credentials, or config paths. The code does not access secrets or environment variables, so requested privileges are proportionate.
✓ 持久化与权限
always is false and the skill does not request persistent/always-on presence or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other privilege concerns.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/3/13
- Initial release of "news-crawler": an automated tool for fetching and summarizing news from specified websites or RSS feeds. - Provides scripts for retrieving news lists and detailed content: `rss_fetcher.py` for RSS sources, `crawl.py` for web pages. - Supports structured daily news report generation, including content extraction and summarization. - Includes usage instructions, workflow, and output formats. - Features guidance on ethical crawling and extensibility for additional features.
● 无害
安装命令 点击复制
官方npx clawhub@latest install news-crawler
镜像加速npx clawhub@latest install news-crawler --registry https://cn.clawhub-mirror.com
技能文档
自动爬取新闻网站和RSS源，提取内容并生成摘要。
快速开始
1. 获取RSS新闻列表
查看可用的新闻源：
python3 scripts/rss_fetcher.py
获取指定RSS源的新闻：
python3 scripts/rss_fetcher.py [max_items]
示例：
python3 scripts/rss_fetcher.py https://www.solidot.org/index.rss 5
2. 爬取具体网页内容
python3 scripts/crawl.py [max_length]
示例：
python3 scripts/crawl.py https://example.com/news/article.html 3000
工作流程
生成新闻日报
- 选择新闻源 - 从常用源中选择或用户提供RSS地址
- 获取新闻列表 - 使用 rss_fetcher.py 获取最新文章
- 爬取详细内容 - 对每篇文章使用 crawl.py 获取全文
- 生成摘要 - 使用 LLM 总结每篇文章的核心内容
- 整理报告 - 按类别或时间排序，生成结构化日报
支持的RSS源
常用中文科技新闻源：
- Solidot: https://www.solidot.org/index.rss
- TechWeb: https://www.techweb.com.cn/rss/all.xml
- 36氪: https://36kr.com/feed
国际源：
- Hacker News: https://news.ycombinator.com/rss
- TechCrunch: https://techcrunch.com/feed/
输出格式
rss_fetcher.py 输出：
{
"items": [
{
"title": "文章标题",
"link": "文章链接",
"description": "简介",
"published": "发布时间"
}
],
"count": 10
}
crawl.py 输出：
{
"url": "原始链接",
"title": "页面标题",
"content": "正文内容",
"length": 5000
}
注意事项
- 尊重robots.txt - 爬取前检查目标网站的爬虫协议
- 控制频率 - 避免频繁请求同一网站
- 内容长度 - 默认截取5000字符，可通过参数调整
- 编码问题 - 脚本已处理UTF-8编码，特殊网站可能需要额外处理
扩展开发
如需支持更多功能，可参考：
- references/rss_sources.md - 更多RSS源列表
- 添加定时任务支持（结合 cron）
- 添加飞书/邮件推送功能
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