IntroductionOn March 31, 2026, Anthropic accidentally exposed the full source code of Claude Code (its flagship ...
Researchers scan 10 million websites and uncover thousands of exposed API keys quietly granting access to cloud systems and ...
An AI pentesting tool has discovered critical vulnerabilities in default ImageMagick configurations. Workarounds offer ...
The exposure traces back to version 2.1.88 of the @anthropic-ai/claude-code package on npm, which was published with a 59.8MB ...
Anthropic's accidental leak has exposed Claude AI's internal code, revealing several unreleased features like Buddy, KAIROS ...
An npm registry for Claude Code was inadvertently made available, and many of Anthropic’s tricks and features are now public ...
Anthropic's Claude Code source has leaked via a packaging error, exposing anti-distillation traps, an undercover mode, and scaffolding for an unreleased agent.
What makes this attack so unsettling is that all the hackers had to do was just steal the password of one of the axios maintainers.
Overview On March 31, NSFOCUS CERT detected that the npm repository of the HTTP client library Axios was poisoned by the supply chain. The attacker bypassed the normal GitHub Actions CI/CD pipeline of ...
Claude Code Source Code Leak Anthropic: Analysts believe the leak could impact the company’s reputation, especially as it is ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results