UnSearch

Search the web, scrape content, and conduct deep research using the UnSearch API. Use when the user needs real-time web search results, content extraction from URLs, fact verification, or multi-source research for AI agents, RAG pipelines, or LLM applications.

This skill appears coherent and only needs your UnSearch API key. Before installing, verify the UnSearch service and docs yourself (https://unsearch.dev), and consider these precautions: (1) keep the API key secret and prefer setting it as an environment variable rather than storing it permanently in a shared config file; (2) avoid asking the skill to fetch internal or non-public URLs (that would send private content to the external API); (3) review UnSearch's privacy and retention policy if you plan to send sensitive content; (4) if you need least privilege, create a limited/ephemeral API key with rate limits or reduced permissions if the provider supports it. If you want deeper assurance, request the UnSearch provider's official SDK or open-source client code and inspect it before use.

Type: OpenClaw Skill Name: unsearch Version: 1.0.0 The OpenClaw UnSearch skill bundle is benign. It provides integration with the UnSearch API for web search, content extraction, and research. All API calls are directed to the legitimate `https://api.unsearch.dev` domain, using an API key for authentication. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the AI agent within the `SKILL.md` or `README.md` files. The code examples are standard HTTP requests, and the documentation is clear and aligned with the stated purpose.