LayerX researchers uncover a flaw in Anthropic's Claude Desktop Extensions that could lead to a RCE vulnerability if ...

Attackers have uploaded over 300 malicious skills to OpenClaw's AI marketplace, turning it into a malware delivery system ...

"Safety alignment is only as robust as its weakest failure mode," Microsoft said in a blog accompanying the research. "Despite extensive work on safety post-training, it has been shown that models can ...

See 10 good vs bad ChatGPT prompts for 2026, with examples showing how context, roles, constraints, and format produce useful answers.

This week’s cyber recap covers AI risks, supply-chain attacks, major breaches, DDoS spikes, and critical vulnerabilities security teams must track.