← 返回 Skills 市场

NosytLabs

Name: NosytLabs
Author: nosytlabs

作者 NosytLabs · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

573

总下载

当前安装

版本数

在 OpenClaw 中安装

/install presearch

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 appears to be an API wrapper for Presearch but crucial metadata is missing. Before installing: (1) ask the publisher/source—do not trust unknown origins; verify the homepage or repository and that this is an official client; (2) require the skill to declare its required API key (e.g., PRESEARCH_API_KEY) in metadata so you can control where the secret is stored; (3) confirm how the agent will supply that key (env var, secret store, or interactive prompt) and whether it will be persisted; (4) limit what you query through this skill (avoid sending sensitive PII or credentials to an external search); (5) prefer skills from known publishers or with verifiable code you can review. If the publisher is verified and the skill's metadata is updated to declare the API key requirement and provenance, the incoherence concern would be resolved.

功能分析

Type: OpenClaw Skill Name: presearch Version: 1.0.0 The skill bundle defines an API interaction for a decentralized search service (Presearch). The `SKILL.md` file describes the API endpoint, authentication (Bearer Token), parameters, and usage examples. There is no evidence of malicious intent, such as data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection attempts against the agent. The external network call to `https://na-us-1.presearch.com/v1/search` is the stated and expected function of this search skill.

能力评估

⚠ Purpose & Capability

The SKILL.md describes a search API that requires a Bearer token and references payments/rate limits, but the skill metadata declares no required environment variables or primary credential. A search integration reasonably needs an API key; omitting that from declared requirements is incoherent. The package also has no homepage or known source to verify the provider.

ℹ Instruction Scope

Instructions are narrowly scoped to calling the provided HTTPS search endpoint with an Authorization header and do not tell the agent to read local files or other system state. However, they include a placeholder for an API key without telling where the agent should obtain it or how it should be supplied, creating ambiguity about how credentials are handled at runtime.

✓ Install Mechanism

Instruction-only skill with no install spec or code files; no artifacts will be written to disk by an installer. This minimizes installation risk.

⚠ Credentials

The API clearly requires a bearer token (Authorization: Bearer YOUR_API_KEY_HERE) but the metadata lists no required env vars or primary credential. That omission is disproportionate and could lead to the agent prompting for or mishandling secrets at runtime. Additionally, the skill claims decentralized/privacy-preserving features that would normally require verifiable provenance or node participation details, none of which are present.

✓ Persistence & Privilege

Skill flags are default (not always-included, agent-invocable allowed). The skill does not request persistent system-wide config or modify other skills. No elevated persistence privileges are requested.

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

Presearch Decentralized Search

元数据

Slug presearch

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题

NosytLabs 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 573 次。

如何安装 NosytLabs？

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

NosytLabs 是免费的吗？

是的，NosytLabs 完全免费（开源免费），可自由下载、安装和使用。

NosytLabs 支持哪些平台？

NosytLabs 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 NosytLabs？

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