Week in review: Claude breached three companies during tests, AD CS domain-takeover PoC released

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 for AI agents, and a proof-of-concept for an Active Directory Certificate Services domain-takeover attack.

Here’s an overview of some of last week’s most interesting news, articles, interviews and videos: Nono: Open-source sandbox for AI agents AI coding agents run with the same permissions as their users, meaning they can access sensitive files, credentials, and production systems. A prompt injection, hallucinated command, or simple mistake can quickly turn that access into a security incident. To reduce the risk, Luke Hinds and Stephen Parkinson co-founded nolabs and released Nono, an open-source … More https://www.helpnetsecurity.com/2026/08/02/week-in-review-claude-breached-three-companies-during-tests-ad-cs-domain-takeover-poc-released/ The post Week in review: Claude breached three companies during tests, AD CS domain-takeover PoC released https://www.helpnetsecurity.com/2026/08/02/week-in-review-claude-breached-three-companies-during-tests-ad-cs-domain-takeover-poc-released/ appeared first on Help Net Security https://www.helpnetsecurity.com .