THREAT LEADERBOARD

威胁情报榜

持续监控 AI 技能生态,发现其他平台漏掉的恶意技能

296 近 7 天新增威胁
12 恶意
77 高危
207 可疑
70 高风险
#21 product-demo-video

Create product demo videos with voiceover, text overlays, and real browser interactions

ClawHub by xiazai77 代码执行
11 小时前
70 高风险
#22 Unknown (E-SafeNet LOCK visible in binary)

Cannot be verified - SKILL.md contains binary data

代码混淆文档欺骗
2 天前
70 高风险
#23 VLAN Linux Client Skill

Manages VLAN.CN virtual networking Linux client installation, configuration, and operation...

供应链凭证窃取文档欺骗
2 天前
70 高风险
#24 gitlab

GitLab operations including creating and cloning repositories, listing projects, managing ...

Hardcoded API ...Hidden script ...Undeclared she...
3 天前
70 高风险
#25 memex

Unified memory plugin for OpenClaw — conversation memory + document search in a single SQL...

未声明的遥测功能base64混淆代码机器标识符外泄
3 天前
68 高风险
#26 skill-registry-unified

一体化技能注册表 - 本地优先匹配,无匹配则自动搜索ClawHub并安全安装

ClawHub by xuwei-stream 代码执行文档欺骗供应链敏感访问
11 小时前
68 高风险
#27 LLM Proxy

Multi-provider LLM API proxy with content security auditing, streaming response detection,...

凭证窃取文档欺骗敏感访问代码执行
2 天前
68 高风险
#28 moodle-connector

Moodle REST API client, batch downloader, and MCP server for Claude Code integration with ...

凭证窃取文档欺骗
2 天前
68 高风险
#29 minimax-web-search

使用 MiniMax Coding Plan API 进行网页搜索和图像理解

凭证窃取文档欺骗供应链
2 天前
68 高风险
#30 recruit-email-monitor

招聘邮件监控系统 - 自动检查邮箱、记录到表格、飞书通知、每日简报

凭证窃取文档欺骗敏感访问
2 天前
68 高风险
#31 deepsafe-scan

Preflight security scanner for AI coding agents - scans deployment config, skills/MCP serv...

文档欺骗权限提升凭证窃取敏感访问
2 天前
68 高风险
#32 kuaidi-query

Query logistics tracking information via Track123 API

凭证窃取权限提升供应链文档欺骗
2 天前
68 高风险
#33 xiaohongshu-win

小红书 Windows 原生工具 - Playwright-based Xiaohongshu content search, topic reports, and note pu...

代码混淆文档欺骗供应链敏感访问
2 天前
68 高风险
#34 zanna-aperta

MCP Bridge completo per OpenClaw con 45 tool per agenti, workspace, progetti, cron, browse...

代码执行文档欺骗敏感访问权限提升
2 天前
68 高风险
#35 skill-factory

Build and publish OpenClaw skills from recurring pain points

代码执行代码混淆供应链文档欺骗
2 天前
68 高风险
#36 agent-p2p

Agent P2P communication skill - enables AI agents to communicate in real-time through a Po...

Hardcoded cred...Remote code ex...Supply chain r...
3 天前
68 高风险
#37 async-command

Async command execution and progress reporting for OpenClaw agents

Hardcoded exte...Sensitive path...Secrets file w...
3 天前
68 高风险
#38 long-term-memory

长期记忆管理系统 - 帮助AI和用户管理、存储、检索长期记忆

硬编码API凭证未声明外部网络通信未声明的付费扣费功能
3 天前
67 高风险
#39 mind-wander

Autonomous background reasoning agent that explores open questions using a local LLM, Falk...

代码执行文档欺骗持久化敏感访问
2 天前
67 高风险
#40 awareness-memory

Persistent cloud memory across sessions with semantic recall, recording, and lookup

数据外泄文档欺骗权限提升供应链
2 天前