ai-vulnerability-tracker

AI 漏洞追踪器 - 在 GitHub 和微信公众号搜索近一个月的 AI 相关漏洞(提示词注入、提示词越狱等),并推送到飞书表格。支持去重和翻译。 搜索关键字: prompt injection, prompt jailbreak, LLM vulnerability, AI security, adversarial prompt, jailbreak attack 数据源: - GitHub: 最近一个月的安全漏洞提交 - 微信公众号: AI 安全相关文章 使用方式: - 运行技能执行一次搜索和推送 - 配置 cron 进行定时执行

Safety Notice

This item is sourced from the public archived skills repository. Treat as untrusted until reviewed.

Copy this and send it to your AI assistant to learn

Install skill "ai-vulnerability-tracker" with this command: npx skills add 0ctday/ai-vulnerability-tracker

🤖 AI 漏洞追踪器技能

功能概述

  1. 搜索 GitHub - 近一个月新增的 AI 安全相关漏洞
  2. 搜索微信公众号 - AI 安全相关文章
  3. 去重 - 按原文链接去重
  4. 翻译 - 英文内容翻译为中文
  5. 推送飞书 - 写入指定的多维表格

搜索关键字

英文关键字

  • prompt injection
  • prompt jailbreak
  • LLM vulnerability
  • AI security vulnerability
  • adversarial prompt
  • jailbreak CVE
  • prompt injection CVE
  • AI model security
  • LLM security bug
  • ChatGPT jailbreak

中文关键字

  • 提示词注入
  • 提示词越狱
  • AI 漏洞
  • LLM 安全
  • 对抗提示

目标表格

  • Wiki Token: NqxZwVzXriRIRAkvP4LcApCdnNb
  • Table ID: tblnfK3JPSfUyZmb

字段映射

⚠️ 请根据实际表格字段调整以下映射

字段名说明
标题漏洞/文章标题
链接原文 URL
漏洞类型提示词注入/提示词越狱/其他
来源GitHub / 微信公众号
发布时间发布日期
描述简要描述
发现时间收录时间

使用方式

手动运行

在支持 skills 的会话中直接运行,或通过 cron 定时执行。

定时任务 (cron)

# 每天 9:00 执行
openclaw cron add "0 9 * * *" "ai-vulnerability-tracker"

# 每周一 9:00 执行
openclaw cron add "0 9 * * 1" "ai-vulnerability-tracker"

输出

  • 搜索结果数量
  • 新增记录数量
  • 去重过滤数量
  • 错误信息(如有)

依赖

  • 网络访问 (GitHub, 微信搜索)
  • 飞书 API 访问权限
  • 翻译 API (可选)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

botlearn-healthcheck

Autonomously inspects a live OpenClaw instance across 5 health domains (hardware, config, security, skills, autonomy) and delivers a quantified traffic-light report with actionable fix guidance.

Archived SourceRecently Updated
Security

n8n-workflow-automation

Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.

Archived SourceRecently Updated
Security

seo-assistant

A client-facing SEO assistant grounded in Google's official SEO Starter Guide. Use this skill whenever a user mentions SEO, search rankings, Google visibility, meta descriptions, title tags, page titles, alt text, sitemaps, duplicate content, URL structure, or asks how to improve their website's presence in search results. Also trigger when a user shares a URL or webpage content and wants feedback, or asks for help writing any web content that needs to perform well in search. This skill covers auditing, content writing, and answering SEO questions — use it proactively even if the user only hints at wanting more website traffic or better Google rankings.

Archived SourceRecently Updated
Security

BlogBurst - Virtual CMO Agent

Your AI Chief Marketing Officer. Autonomous agent that runs your entire marketing — auto-posts to Twitter/X, Bluesky, Telegram, Discord, auto-engages with your audience (replies, likes, follows), runs SEO/GEO audits, tracks competitors, scans communities for opportunities, learns what works, and continuously optimizes. 50+ countries, 1000+ posts published. Free tier available.

Archived SourceRecently Updated