← 返回 Skills 市场
94
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install search-agent
功能描述
AI-powered search agent that performs intelligent web searches, aggregates results, and provides summarized answers with source citations. Use when: user nee...
安全使用建议
This skill appears to implement a legitimate web-search and summarization tool, but there are a few things to check before installing or using it:
- Confirm required credentials: the SKILL.md and index.js reference SEARCH_API_KEY and AI_MODEL, but the registry metadata declares none. You should assume an API key is needed; ask the publisher or check the upstream repository for which search service and key format are required.
- Verify source provenance: registry 'Source' is unknown while package.json points to github.com/clawhub/search-agent. Inspect that repository (or the uploaded files) to ensure it matches and is maintained by a trustworthy owner.
- Network behavior: the skill will fetch arbitrary webpages and call search APIs. Do not run it in an environment containing sensitive internal-only URLs you don't want exposed. Avoid giving it private or sensitive queries unless you control the search target and understand where requests go.
- Review dependencies & run audits: the package uses axios and cheerio (common), but run a dependency audit and optionally sandbox execution before granting it access to production systems.
- Ask for clarification: request that the publisher update the registry metadata to list SEARCH_API_KEY (and any other required env vars) and provide the concrete search API endpoints used (performSearch currently contains placeholder endpoints).
If the publisher confirms the above and provides a verifiable source repo/release, and you only provide the minimal API key with rate/permission controls, the inconsistencies would be explainable and the risk lowered.
功能分析
Type: OpenClaw Skill
Name: search-agent
Version: 1.0.0
The search-agent skill bundle is a well-documented template for an AI-powered research tool. The core logic in index.js uses standard libraries like axios and cheerio to fetch and parse web content, while cli.js provides a functional command-line interface. The SKILL.md and README.md files provide clear instructions and architectural overviews without any evidence of prompt injection or malicious intent. Although the search API integration is currently a placeholder, the code lacks any high-risk behaviors such as data exfiltration, unauthorized execution, or obfuscation.
能力评估
Purpose & Capability
The skill's name/description (web search, summarization) aligns with the code and README: axios/cheerio are used to fetch and parse web pages and the module exposes search, quickSearch, factCheck, etc. Requiring a search API key and AI model for summarization is coherent with the stated purpose. However the registry metadata lists no required environment variables/credentials even though both SKILL.md and index.js reference SEARCH_API_KEY and AI_MODEL — a provenance/metadata inconsistency.
Instruction Scope
The SKILL.md instructions and the code focus on web search, content fetching, analysis, and formatting. The runtime instructions do not ask the agent to read unrelated local files or other credentials. The code fetches arbitrary URLs returned by search results (normal for a search tool), which means it will make outbound network requests and retrieve remote content.
Install Mechanism
No install spec is provided (instruction-only at registry level), which is low-risk for installation. The package includes code files and a package.json with dependencies (axios, cheerio) so the skill can be executed if installed via npm; there is no download-from-arbitrary-URL or extract step. Still, the registry/source is listed as 'unknown' while package.json points to a GitHub repo — source provenance should be confirmed before installing.
Credentials
The SKILL.md and index.js both reference environment variables (SEARCH_API_KEY, AI_MODEL, SEARCH_MAX_RESULTS, SEARCH_TIMEOUT, SEARCH_LANGUAGE). The registry metadata, however, declares no required env vars or primary credential. SEARCH_API_KEY (and potentially an AI_MODEL credential) is reasonable for this skill, but the failure to declare required credentials in the registry is a mismatch that could hide needed secrets. No unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated system persistence. It does not modify other skills or claim to write system-wide configuration. It will make outbound HTTP requests when invoked, which is expected for a search agent.
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 search-agent - 安装完成后,直接呼叫该 Skill 的名称或使用
/search-agent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 search-agent v1.0.0.
- Aggregates and summarizes search results from web, news, academic, code, and image sources.
- Provides AI-powered analysis with source citation, fact verification, and credibility scoring.
- Delivers structured, cited responses including key findings, sources, and related queries.
- Supports advanced search operators and customization for result count, source filters, and language preferences.
元数据
常见问题
Search Agent Skill 是什么?
AI-powered search agent that performs intelligent web searches, aggregates results, and provides summarized answers with source citations. Use when: user nee... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 94 次。
如何安装 Search Agent Skill?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install search-agent」即可一键安装,无需额外配置。
Search Agent Skill 是免费的吗?
是的,Search Agent Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Search Agent Skill 支持哪些平台?
Search Agent Skill 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 Search Agent Skill?
由 bittao(@hgta23)开发并维护,当前版本 v1.0.0。
推荐 Skills