Cybernews

AI assistant runs hacker’s commands just from opening a project: critical vulnerability found in Claude Code

Claude Code would execute hidden code from untrusted projects before any user confirmation, Check Point reports.
The Hacker News

Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration

Claude Code flaws allow remote code execution and API key theft via untrusted repositories; three bugs fixed across 2025–2026 releases.
GovInfoSecurity

Malicious Repo Files Could Hijack Claude Code Sessions

Check Point research found three critical flaws in Anthropic's Claude Code that allow attackers to execute arbitrary commands and steal API keys through repository ...
SecurityWeek

Claude Code Flaws Exposed Developer Devices to Silent Hacking

Vulnerabilities in Anthropic’s Claude Code tool could have allowed attackers to silently gain control of a developer’s computer.
TechJuice

Researchers Claim Malicious Repositories Turn Claude Code Into an Ideal Hacker’s Tool

Security researchers disclose critical vulnerabilities in Anthropic’s Claude Code that allow remote code execution and credential theft.
Hosted on MSN

Google previews Code Wiki: Can you trust AI to document your repository?

Documenting code can be dull, but explaining the source code of a complex project is hard for AI to get right Google has previewed Code Wiki, an AI project that aims to document code in a repository ...
Hackaday

Dump A Code Repository As A Text File, For Easier Sharing With Chatbots

Some LLMs (Large Language Models) can act as useful programming assistants when provided with a project’s source code, but experimenting with this can get a little tricky if the chatbot has no way to ...