by 安全扫描
OpenClaw
安全
medium confidence该技能的代码和指令与其所述目的（网页内容获取）一致，它使用HTTP客户端获取网页，请求适当的配置，不请求无关的凭证或意外端点。
评估建议
此技能似乎确实做到了它声称的：网页内容获取脚本，用于获取和解析网页内容。安装或运行之前：1) 确认您对授予网络访问权限感到满意——该工具可以访问任何URL。2) 仅将其用于您有权访问的网站，避免访问受保护的内容，除非您完全信任设置。3) 技能不请求凭证，但注意不要向工具传递敏感的URL或凭证，除非您信任整个工具链。4) 如果您想要更高的保证，请在运行前在本地审查包含的脚本。...详细分析 ▾
ℹ 用途与能力
The skill's name, description, SKILL.md, and included scripts consistently implement fetching webpages through r.jina.ai, markdown.new, and defuddle.md. One minor mismatch: the repository metadata declares no required binaries, but both included scripts invoke curl; the skill therefore implicitly requires curl to be present.
ℹ 指令范围
The SKILL.md and scripts stay within the stated scope (try web_fetch then fall back to the listed services). However the tool will transmit the target URL (and the fetched page content) to third‑party services — this can leak sensitive URLs or query parameters. The scripts do not URL‑encode or sanitize inputs and will forward whatever URL the user supplies. No instructions read local files or environment variables beyond typical execution.
✓ 安装机制
No install spec or remote download is used; the skill is instruction+code only (two small scripts included). Nothing is fetched or extracted during install, so installation risk is low.
✓ 凭证需求
The skill requests no credentials or environment variables, which is proportionate for its purpose. It does, however, rely on network access to external services; no secrets are required or collected by the code.
✓ 持久化与权限
The skill does not request persistent/always presence and does not modify other skills or system configuration. It runs on demand and has no elevated privileges.
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
latestv1.0.12026/3/6
初始版本，支持网页内容获取
● 可疑
安装命令 点击复制
官方npx clawhub@latest install web-content-fetcher
镜像加速npx clawhub@latest install web-content-fetcher --registry https://cn.clawhub-mirror.com
技能文档
当常规 web_fetch/web_search 无法获取内容时，使用替代服务获取网页 Markdown 格式内容。
支持的服务
| 优先级 | 服务 | 用法 | 适用场景 |
|---|---|---|---|
| 1 | r.jina.ai | https://r.jina.ai/{url} | 最稳定，通用性强 |
| 2 | markdown.new | https://markdown.new/{url} | Cloudflare 保护网站 |
| 3 | defuddle.md | https://defuddle.md/{url} | 备用方案 |
使用方法
直接调用
当需要获取网页内容时，按顺序尝试：
- 首先用
web_fetch尝试获取 - 如果失败或被过滤，调用本工具
# 使用 jina.ai (首选)
curl -s "https://r.jina.ai/https://example.com"# 使用 markdown.new (Cloudflare)
curl -s "https://markdown.new/https://example.com"
# 使用 defuddle.md (备用)
curl -s "https://defuddle.md/https://example.com"
API 格式
# 简单获取
fetch_webpage # 指定方法
fetch_webpage --method jina|markdown|defuddle
示例
用户: 帮我获取 https://news.example.com/article/123 的内容
助手: (使用 r.jina.ai 获取)
工具脚本
本目录包含 fetch.sh 脚本，可直接调用：
./fetch.sh https://example.com
./fetch.sh https://example.com jina
让网页内容获取不再受限 🌐
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