← 返回 Skills 市场

presearch

Name: presearch
Author: nosytlabs

作者 NosytLabs · GitHub ↗ · v1.0.1

cross-platform ⚠ suspicious

569

总下载

当前安装

版本数

在 OpenClaw 中安装

/install decentralized-search

功能描述

Production-ready decentralized search for AI agents. Privacy-first, uncensored web search via distributed node infrastructure.

使用说明 (SKILL.md)

Presearch Search API

Endpoint: https://na-us-1.presearch.com/v1/search
Method: GET
Auth: Bearer Token
Rate Limit: 100 requests/minute

Authentication

Authorization: Bearer YOUR_API_KEY_HERE

Parameters

Parameter	Type	Required	Default	Description
`q`	string	✅	-	Search query
`lang`	string	❌	en-US	Language code
`time`	string	❌	any	any, day, week, month, year
`page`	string	❌	1	Page number
`safe`	string	❌	1	Safe search

Response

{
  "data": {
    "standardResults": [
      {
        "title": "string",
        "link": "string",
        "description": "string"
      }
    ],
    "pagination": {
      "current_page": 1,
      "has_next": true
    }
  }
}

Error Codes

401: Invalid API key
402: Payment required
422: Invalid parameters
429: Rate limit exceeded

Usage

# Python
with PresearchSkill(api_key) as skill:
    results = skill.search("AI agents")

// Node.js
const results = await skill.search({ query: "AI agents" });

Privacy Features

No tracking or profiling
Decentralized node network
Encrypted traffic
Uncensored results

安全使用建议

This skill's documentation shows it needs a Presearch API key and calls a presearch.com endpoint, but the registry entry didn't declare any required credentials or a source URL. Before installing: 1) Ask the publisher for the source/homepage and confirm the official Presearch endpoint and auth model; 2) Confirm how/where the API key should be supplied (and that the skill will not try to read unrelated secrets); 3) Prefer skills that declare required.env/primary credential so you can safely manage tokens; 4) Because this is instruction-only, it won't install code, but the metadata mismatch is a red flag — treat it as untrusted until the author provides clarifying metadata or a verified source.

功能分析

Type: OpenClaw Skill Name: decentralized-search Version: 1.0.1 The skill bundle contains standard metadata and a `SKILL.md` file that serves as documentation for integrating with the Presearch Search API. The markdown content accurately describes the API endpoint, parameters, authentication, and usage examples. There are no instructions that attempt prompt injection against the AI agent, nor any code or instructions indicative of data exfiltration, malicious execution, persistence mechanisms, or obfuscation. All content aligns with the stated purpose of providing a decentralized search capability.

能力评估

⚠ Purpose & Capability

The SKILL.md documents a Presearch HTTP API (Bearer token auth to https://na-us-1.presearch.com/v1/search). The skill description matches that purpose, but the registry metadata lists no required environment variables or primary credential and provides no source/homepage. A search-integration skill would reasonably need an API key declared; its absence is an incoherence.

ℹ Instruction Scope

The instructions themselves are narrowly scoped: how to call the GET /v1/search endpoint, parameters, responses, and example snippets. They do not ask the agent to read local files or other unrelated secrets. The notable issue is that the instructions assume an API key (Authorization: Bearer YOUR_API_KEY_HERE) while the skill metadata does not declare one.

✓ Install Mechanism

This is an instruction-only skill with no install spec or code files, so nothing is written to disk or downloaded. That minimizes install-time risk.

⚠ Credentials

The runtime docs clearly require a bearer API key (the examples use api_key), but requires.env and primary credential are empty in the registry entry. This mismatch could lead to unclear handling of credentials (where should the key be provided?) and increases the risk of misconfiguration or accidental credential exposure if implementers improvise.

✓ Persistence & Privilege

The skill is not marked always:true and uses default autonomous invocation settings. It does not request persistent system-wide privileges or modify other skills' configs according to the provided metadata.

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 decentralized-search
安装完成后，直接呼叫该 Skill 的名称或使用 /decentralized-search 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

v1.0.1

https://github.com/NosytLabs/presearch-search-skill

元数据

Slug decentralized-search

版本 1.0.1

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题

presearch 是什么？

Production-ready decentralized search for AI agents. Privacy-first, uncensored web search via distributed node infrastructure. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 569 次。

如何安装 presearch？

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

presearch 是免费的吗？

是的，presearch 完全免费（开源免费），可自由下载、安装和使用。

presearch 支持哪些平台？

presearch 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 presearch？

由 NosytLabs（@nosytlabs）开发并维护，当前版本 v1.0.1。