LinkedIn

低风险
作者:biostartechnology | 审计时间:2026-02-26T09:59:20.936Z | 规则集:0.2.0

快速安装

将技能安装到你的 Agent

clawhub install linkedin

技能介绍

通过 browser relay 或 cookies 实现 LinkedIn 自动化,用于消息发送、个人资料查看和人脉操作。

使用场景

文档(原文)

来源:SKILL.md
以下为作者原文(通常为英文)。安装请以页面顶部“快速安装”为准。

name: linkedin
description: LinkedIn automation via browser relay or cookies for messaging, profile viewing, and network actions.
homepage: https://linkedin.com
metadata: {"clawdbot":{"emoji":"💼"}}

LinkedIn

Use browser automation to interact with LinkedIn - check messages, view profiles, search, and send connection requests.

Connection Methods

Option 1: Chrome Extension Relay (Recommended)

  1. Open LinkedIn in Chrome and log in
  2. Click the Clawdbot Browser Relay toolbar icon to attach the tab
  3. Use browser tool with profile="chrome"

Option 2: Isolated Browser

  1. Use browser tool with profile="clawd"
  2. Navigate to linkedin.com
  3. Log in manually (one-time setup)
  4. Session persists for future use

Common Operations

Check Connection Status

browser action=snapshot profile=chrome targetUrl="https://www.linkedin.com/feed/"

View Notifications/Messages

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/messaging/"
browser action=snapshot profile=chrome

Search People

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/search/results/people/?keywords=QUERY"
browser action=snapshot profile=chrome

View Profile

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/in/USERNAME/"
browser action=snapshot profile=chrome

Send Message (confirm with user first!)

  1. Navigate to messaging or profile
  2. Use browser action=act with click/type actions
  3. Always confirm message content before sending

Safety Rules

  • Never send messages without explicit user approval
  • Never accept/send connection requests without confirmation
  • Avoid rapid automated actions - LinkedIn is aggressive about detecting automation
  • Rate limit: ~30 actions per hour max recommended

Session Cookie Method (Advanced)

If browser relay isn't available, extract the li_at cookie from browser:

  1. Open LinkedIn in browser, log in
  2. DevTools → Application → Cookies → linkedin.com
  3. Copy li_at value
  4. Store securely for API requests

Troubleshooting

  • If logged out: Re-authenticate in browser
  • If rate limited: Wait 24 hours, reduce action frequency
  • If CAPTCHA: Complete manually in browser, then resume

安全审计

低风险

摘要

通过 browser relay 或 cookies 实现 LinkedIn 自动化,用于消息发送、个人资料查看和人脉操作。

风险画像 危险 隐私 范围 声誉 质量

ToxicSkills 分析

黑名单
未命中
提示词注入
未检测到

当前静态检测未发现 Toxic 信号。

关键风险 0 项

暂无 LLM 风险要点(LLM 未启用或无缓存)。

确定性发现(证据)

未检测到发现。

评分标准

每个技能从 5 个维度评分,加权总分决定星级。

代码毒性 100/100 (权重 30%)
隐私风险 100/100 (权重 25%)
权限范围 100/100 (权重 20%)
作者声誉 75/100 (权重 15%)
代码质量 70/100 (权重 10%)

星级说明

5★ 安全 — 总分 ≥ 80
4★ 良好 — 总分 70–79
3★ 注意 — 总分 60–69
2★ 有风险 — 总分 40–59
1★ 危险 — 总分 < 40

为何是这个评分?

所有维度均高于 60 分,该技能通过安全基线。

更多技能

VettedSkillsHub

从 ClawHub(ClawdBot / OpenClaw 官方市场)精选下载量前 100 的技能,进行独立 5 维度安全审计。证据透明可查,评分可复现,一键安装。

关于

本站评分为 best-effort 静态分析,分数可复现、证据可追溯。在敏感环境中仍应进行人工审计与隔离部署。

© 2026 VettedSkillsHub。ClawdBot 和 OpenClaw 为社区项目。