Tech Times on MSN

Summarizing website in Claude code auto mode can compromise your machine; no fix planned

Claude Code Auto Mode security exploit: Johann Rehberger's Python module-shadowing attack achieves remote code execution 60-80 percent of the time against a feature Anthropic marketed with a 0.00 ...
The Next Web

A researcher hijacked Claude Code by asking it to summarise a web page

A researcher tricked Claude Code into running attacker code up to 80% of the time. Anthropic says the behaviour is working as designed.

Anthropic has a cute graphic showing how its AI spread 'malicious' code

Anthropic said it was "most concerned" about an event in which Claude uploaded "malicious" code. To help explain the incident ...
XDA Developers on MSN

Anthropic analyzed 400,000 Claude Code sessions, and it turns out there's a right way to use it

The data says you’re probably using it wrong ...
Forbes

Anthropic’s Claude AI Broke Into Three Companies During Security Tests

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Anthropic disclosed its Claude models breached three real companies' production systems ...