North Korean-linked campaign publishes 26 malicious npm packages hiding C2 in Pastebin, deploying credential stealers & RAT ...

A developer-targeting campaign leveraged malicious Next.js repositories to trigger a covert RCE-to-C2 chain through standard ...

Anthropic 刚推出 Skills [1]时，我非常兴奋。官方的态度也很明确：不要再执着于开发复杂 Agent，而是把精力放在 Skills 上。但在认真研究了一圈官方和社区的 Skills 示例[2]后，我很快冷静下来—— 几乎没有一个 ...

While the Windows maker did not attribute the activity to a specific threat actor, the use of VS Code tasks and Vercel ...

Linked to North Korean fake job-recruitment campaigns, the poisoned repositories are aimed at establishing persistent C2 ...

Anthropic updates tool calling to reduce token use; tool search cuts tokens up to 80%, making larger tool sets practical.

When someone asks ChatGPT, Claude, Gemini, or Copilot to read a webpage, the AI decides what the user sees — not your layout, not your ad tags, and not your structured data. Most of what you put on ...

还在纠结 Claude Code 的各种“黑魔法”怎么玩？Command、Subagent、Skills 到底有什么区别，各自适合什么场景？新出来的 Programmatic Tool Calling 又是啥，真的能提升「代码质量 + 开发效率」吗？因为一个工具不得不搭梯子，有没有体验接近、甚至更灵活的「平替」方案？本次分享将带你彻底搞懂～Claude Code ...