Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

exa-enterprise-rbacexa 企业 rbac

Agent Skill

exa-enterprise-rbac 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

588

周安装

25

GitHub Stars

2,111

下载量

206
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:exa-enterprise-rbac(exa 企业 rbac)
来源仓库:https://github.com/jeremylongshore/claude-code-plugins-plus-skills
仓库路径:skills/exa-enterprise-rbac
安装命令:
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill exa-enterprise-rbac
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill exa-enterprise-rbac

简介

exa-enterprise-rbac 通过 API Key 作用域与应用层控制实现企业级访问管理。

  • 适用于多团队协作环境下隔离资源、限制域名访问与监控用量分配的场景。
  • 采用 key-per-use-case 架构分离不同用途密钥,增强安全性与审计能力。
  • 使用前需开通企业版账户并创建多个专用 API Key 进行分类管控。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Exa Enterprise RBAC

Overview

Manage access to Exa search API through API key scoping and application-level controls. Exa is API-key-based (no built-in RBAC), so access control is implemented through multiple API keys per use case, application-layer permission enforcement, domain restrictions per team, and per-key usage monitoring.

Prerequisites

  • Exa API account with team/enterprise plan
  • Dashboard access at dashboard.exa.ai
  • Multiple API keys for key isolation

Instructions

Step 1: Key-Per-Use-Case Architecture

// config/exa-keys.ts
import Exa from "exa-js";

// Create separate clients for each use case
const exaClients = {
  // High-volume RAG pipeline — production key with higher limits
  ragPipeline: new Exa(process.env.EXA_KEY_RAG!),

  // Internal research tool — lower volume key
  researchTool: new Exa(process.env.EXA_KEY_RESEARCH!),

  // Customer-facing search — separate key for isolation
  customerSearch: new Exa(process.env.EXA_KEY_CUSTOMER!),
};

export function getExaForUseCase(
  useCase: keyof typeof exaClients
): Exa {
  const client = exaClients[useCase];
  if (!client) throw new Error(`No Exa client for use case: ${useCase}`);
  return client;
}

Step 2: Application-Level Permission Enforcement

// middleware/exa-permissions.ts
interface ExaPermissions {
  maxResults: number;
  allowedTypes: ("auto" | "neural" | "keyword" | "fast" | "deep")[];
  allowedCategories: string[];
  includeDomains?: string[];     // restrict to these domains
  dailySearchLimit: number;
}

const ROLE_PERMISSIONS: Record<string, ExaPermissions> = {
  "rag-pipeline": {
    maxResults: 10,
    allowedTypes: ["neural", "auto"],
    allowedCategories: [],
    dailySearchLimit: 10000,
  },
  "research-analyst": {
    maxResults: 25,
    allowedTypes: ["neural", "keyword", "auto", "deep"],
    allowedCategories: ["research paper", "news"],
    dailySearchLimit: 500,
  },
  "marketing-team": {
    maxResults: 5,
    allowedTypes: ["keyword", "auto"],
    allowedCategories: ["company", "news"],
    dailySearchLimit: 100,
  },
  "compliance-team": {
    maxResults: 10,
    allowedTypes: ["keyword", "auto"],
    allowedCategories: [],
    includeDomains: ["nist.gov", "owasp.org", "sans.org", "sec.gov"],
    dailySearchLimit: 200,
  },
};

function validateSearchRequest(
  role: string,
  searchType: string,
  numResults: number,
  category?: string
): { allowed: boolean; reason?: string } {
  const perms = ROLE_PERMISSIONS[role];
  if (!perms) return { allowed: false, reason: "Unknown role" };
  if (!perms.allowedTypes.includes(searchType as any)) {
    return { allowed: false, reason: `Search type ${searchType} not allowed for ${role}` };
  }
  if (numResults > perms.maxResults) {
    return { allowed: false, reason: `Max ${perms.maxResults} results for ${role}` };
  }
  if (category && perms.allowedCategories.length > 0 && !perms.allowedCategories.includes(category)) {
    return { allowed: false, reason: `Category ${category} not allowed for ${role}` };
  }
  return { allowed: true };
}

Step 3: Domain Restrictions per Team

// Enforce domain restrictions so compliance-sensitive teams
// only see results from vetted sources
async function enforcedSearch(
  exa: Exa,
  role: string,
  query: string,
  opts: any = {}
) {
  const perms = ROLE_PERMISSIONS[role];
  if (!perms) throw new Error(`Unknown role: ${role}`);

  const validation = validateSearchRequest(
    role,
    opts.type || "auto",
    opts.numResults || 10,
    opts.category
  );
  if (!validation.allowed) throw new Error(validation.reason);

  return exa.searchAndContents(query, {
    ...opts,
    numResults: Math.min(opts.numResults || 10, perms.maxResults),
    type: opts.type || "auto",
    // Merge domain restrictions from role permissions
    includeDomains: perms.includeDomains || opts.includeDomains,
  });
}

Step 4: Per-Key Usage Tracking

// Track usage per API key / role for budget enforcement
class KeyUsageTracker {
  private usage = new Map<string, { count: number; resetAt: number }>();

  checkAndIncrement(role: string): void {
    const perms = ROLE_PERMISSIONS[role];
    if (!perms) throw new Error(`Unknown role: ${role}`);

    const now = Date.now();
    const dayStart = new Date().setHours(0, 0, 0, 0);
    let entry = this.usage.get(role);

    if (!entry || entry.resetAt < now) {
      entry = { count: 0, resetAt: dayStart + 24 * 60 * 60 * 1000 };
    }

    if (entry.count >= perms.dailySearchLimit) {
      throw new Error(
        `Daily search limit (${perms.dailySearchLimit}) exceeded for ${role}`
      );
    }

    entry.count++;
    this.usage.set(role, entry);
  }

  getUsage(role: string) {
    const entry = this.usage.get(role);
    const limit = ROLE_PERMISSIONS[role]?.dailySearchLimit || 0;
    return {
      used: entry?.count || 0,
      limit,
      remaining: limit - (entry?.count || 0),
    };
  }
}

Step 5: Key Rotation Procedure

set -euo pipefail
# 1. Create new key in Exa dashboard (dashboard.exa.ai)
# 2. Deploy new key alongside old key
# 3. Verify new key works
curl -s -o /dev/null -w "%{http_code}" \
  -X POST https://api.exa.ai/search \
  -H "x-api-key: $NEW_EXA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"key rotation test","numResults":1}'

# 4. Switch traffic to new key
# 5. Monitor for errors
# 6. Revoke old key in dashboard after 24h

Error Handling

IssueCauseSolution
401 on searchInvalid or revoked API keyRegenerate in dashboard
429 rate limitedKey-level rate limit exceededDistribute across keys
Daily limit hitSearch budget exhaustedAdjust limits or wait for reset
Wrong domain resultsMissing domain filterApply includeDomains per role

Resources

Next Steps

For policy enforcement, see exa-policy-guardrails. For multi-env setup, see exa-multi-env-setup.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.52%
按下载量换算73

Claude

30.68%
按下载量换算63

Cursor

20.78%
按下载量换算43

Gemini CLI

8.71%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills