mdgs-tavily-search-skill

使用 Tavily API 进行网络搜索、网页内容提取、抓取、映射和研究。当用户需要搜索信息、获取网页内容、从网站抓取数据、绘制网站地图或进行深度研究时使用此技能。AI 应根据任务自动选择最合适的模式。

This skill appears to do what it claims (a Tavily-based search/crawl client), but the package metadata omitted the required API credential. Before installing or running it: 1) Confirm the provenance of @tavily/core and tavily.com (verify official package/website and review the package source on the registry). 2) Expect to supply TAVILY_API_KEY — treat it as a secret and do not paste long-lived credentials into shared prompts or public places. 3) Inspect the @tavily/core package code (or vendor docs) to see exactly what data (URLs, page content, queries) will be sent to the Tavily service. 4) Run the skill in an isolated environment or container if you must test it, and avoid running it with credentials that grant broad access elsewhere. 5) If you will use crawling/extraction, ensure you respect robots.txt, privacy/legal constraints, and limit maxPages/depth to avoid large accidental data exfiltration. If the skill is published to a registry, ask the publisher to update the metadata to declare TAVILY_API_KEY as a required credential and include homepage/provenance details before wider use.

Type: OpenClaw Skill Name: mdgs-tavily-search-skill Version: 1.0.0 The skill is a legitimate integration of the Tavily Search API, providing capabilities for web searching, crawling, and content extraction. The core logic in `scripts/tavily.js` uses the official `@tavily/core` library and follows standard practices for handling API keys via environment variables, with no evidence of malicious intent, data exfiltration, or prompt injection.