← 返回 Skills 市场
billyutw

Web Search

作者 billyutw · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
38102
总下载
32
收藏
561
当前安装
1
版本数
在 OpenClaw 中安装
/install web-search
功能描述
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
安全使用建议
Install only if you are comfortable sending search terms to DuckDuckGo through the dependency it installs. Do not search for secrets, credentials, confidential business data, or highly sensitive personal information, and use --output only with intended non-sensitive file paths because existing files may be overwritten.
功能分析
Type: OpenClaw Skill Name: web-search Version: 1.0.0 The skill provides web search functionality using the legitimate `duckduckgo-search` library. The `SKILL.md` documentation is clear and does not contain any prompt injection attempts or instructions for malicious behavior. The `scripts/search.py` code is well-structured and primarily interacts with the DuckDuckGo API. However, the script includes a `--output` argument that allows writing search results to an arbitrary file path specified by the user. While this is a documented and plausible feature for saving results, it represents a file write capability that, if misused by a compromised or maliciously prompted agent, could lead to writing data to sensitive system locations. This constitutes a risky capability without clear malicious intent, classifying it as suspicious.
能力评估
Purpose & Capability
The artifacts consistently implement web, news, image, and video search through the duckduckgo_search library, with formatting and filtering features matching the stated purpose.
Instruction Scope
The activation guidance is broad for research and fact-checking, but it remains tied to explicit web search/current-information use and does not instruct hidden autonomous behavior.
Install Mechanism
Installation requires pip installing the third-party duckduckgo-search package without a pinned version, which is purpose-aligned but carries normal supply-chain trust considerations.
Credentials
Search queries are sent to DuckDuckGo as expected for this skill; the documentation discloses DuckDuckGo use but could be clearer about privacy implications for sensitive queries.
Persistence & Privilege
The optional --output feature writes results to a caller-supplied path and creates parent directories, with no overwrite guard; this is disclosed and user-directed but should be used cautiously.
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 web-search
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /web-search 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
web-search 1.0.0 - Initial release of the skill. - Search the web using DuckDuckGo’s API for web pages, news, images, and videos. - Supports multiple result formats: plain text, markdown, and JSON. - Includes rich filtering (time range, region, safe search) and content-type options. - Image and video searches offer flexible filters (size, color, type, duration, resolution, layout). - Allows saving results to files for further use.
元数据
Slug web-search
版本 1.0.0
许可证
累计安装 1282
当前安装数 561
历史版本数 1
常见问题

Web Search 是什么?

This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 38102 次。

如何安装 Web Search?

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

Web Search 是免费的吗?

是的,Web Search 完全免费(开源免费),可自由下载、安装和使用。

Web Search 支持哪些平台?

Web Search 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 Web Search?

由 billyutw(@billyutw)开发并维护,当前版本 v1.0.0。

💬 留言讨论