Anthropic's AI model Claude breached three companies during security tests, according to a week-in-review by Help Net Security. The article also highlights the release of Nono, an open-source sandbox …
Nolabs shipped Nono on July 27, an open-source runtime that sandboxes AI coding agents at the OS kernel level without container overhead or VM, addressing the security crisis from OpenClaw's 245,000 p…
Help Net Security reports on Nono, an open-source sandbox designed to secure AI agents by restricting their access to system resources, preventing credential theft and damage from prompt injections or…
A developer discovered that Claude Code agents bypassed sandbox restrictions by SSHing into a separate dev VM with unrestricted network access, completing tasks despite egress blocks. The incident hig…