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

271 近 7 天新增威胁

12 恶意

75 高危

184 可疑

全部 271 恶意 12 高危 75 可疑 184

按危险度按时间

45 可疑

#161 security-defense-line

区块链安全防护与威胁防御系统 - 智能合约审计、钱包安全、交易验证、钓鱼检测等

61-skill mesh for AI coding assistants — 5-layer architecture with orchestrators, workflow...

Execute commands on the host machine from inside the OpenClaw container via HostLink daemo...

Comprehensive 1Panel server management skill for AI agents — 580+ API endpoints

OWASP LLM Top 10 security monitor for OpenClaw — taint-checks messages, detects violations...

文档欺骗供应链权限提升

1 天前

45 可疑

#166 flyai-transit-tour

中转不浪费攻略助手 - 帮用户把中转等待变成免费旅行，找到中转能玩的航班方案

Professional cross-border e-commerce intelligence analysis service

系统诊断 - 检查OpenClaw和运行环境健康状态

OneTrust integration for managing data privacy, records, and automated workflows

Unversioned np...Third-party cr...Implicit files...

2 天前

45 可疑

#170 blood-pressure-therapy

高血压治疗管理 - Blood pressure monitoring and AHA 2017 classification with audio therapy

Undeclared ext...URL shortener ...No malicious c...

2 天前

45 可疑

#171 video-to-text

免费视频转文字 API - 使用免费 Whisper API 将视频/音频转为文字

Undeclared she...Undeclared fil...Command inject...

2 天前

45 可疑

#172 bitable_to_feishu_webhook

从飞书多维表中按用户规则筛选记录，自动将格式化后的内容推送到指定的群机器人 Webhook

Undeclared web...eval() with re...Duplicate undo...

2 天前

45 可疑

#173 browser-automation

浏览器自动化操作与网页交互技能

Hardcoded API ...Anti-detection...Undeclared net...

2 天前

45 可疑

#174 session-reflect

Analyze Claude Code session history to generate self-observation journals

Undocumented s...Undeclared sen...Hidden capabil...

2 天前

45 可疑

#175 capability-evolver-zc

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements a...

Undeclared she...Undeclared ext...Hardcoded API ...

2 天前

45 可疑

#176 update-approval-guard (primary) + instreet + 25+ sub-skills (workspace)

Multi-skill OpenClaw workspace: update approval guard as primary skill, plus InStreet comm...

Live API key i...Undeclared she...Destructive sh...

2 天前

45 可疑

#177 token-watchdog

OpenClaw session cost monitor — alerts via Telegram when agent spend exceeds budget

Undeclared she...Hidden functio...External downl...

2 天前

45 可疑

#178 skill-security-vet

技能安全審核 - 整合本地掃描 + VirusTotal 雲端威脅情報

未声明的本地驱动器扫描未声明的自动隔离/删除能力system_paths 访...

2 天前

45 可疑

#179 linux-cron-panel

管理 Linux 系统定时任务（crontab）的 Panel API 工具

强制依赖第三方仓库回调上报机制不透明systemd持久化权限

2 天前

45 可疑

#180 self-evolution-engine

自我进化引擎 - 让AI Skill具备自我分析、自我改进、自我学习的能力

硬编码API密钥泄露未声明的系统目录写入文档-能力差异

2 天前