Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

作为一个完全用 AI 写出来的编程工具，Claude Code 官方仓库里的用户反馈几乎每天都在刷新。近期就有用户称，自 2 月更新后，Claude Code 在复杂工程任务中的表现明显退化，已经“无法被信任用于复杂工程工作”。该 issue 已被关闭，但内容提供了一份非常详细的用户侧实测报告。

Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...

Three critical security vulnerabilities in Anthropic’s AI-powered coding tool, Claude Code, exposed developers to full machine takeover and credential theft simply by opening a project repository.

Discover the top 12 tools in 2026, from Cursor to Copilot, to speed up daily dev workflows and build apps faster!

When a coding assistant starts looking like it’s cutting corners, developers notice. A senior director in AMD’s AI Group has publicly needled Anthropic’s Claude Code for what she calls a tendency to ...

Anthropic’s Claude models are now generally available in Microsoft Foundry, giving Azure developers and enterprise application teams another major frontier model option inside Microsoft’s cloud AI ...

The fact that Claude Sonnet 4.6 eclipses every other frontier model on the market in programming workflows is pretty well-established. If there was any lingering skepticism, the extensive benchmarks I ...