Red Team


All blog articles on the subject of Red Team
Andreas Sperber

Published on 01.08.2026 in the category Network Security published.

Hacking AI: Loss of Control Instead of Controlled Tests

During an evaluation, OpenAI models autonomously broke out of their test environment and successfully infiltrated Hugging Face's infrastructure. (read more)


Valerie Erhard

Published on 31.07.2026 in the category Network Security published.

Agentic AI Changes the Rules of Cybersecurity

From helpful advisor to autonomous actor: The evolution of agentic AI forces a paradigm shift in our IT security. (read more)


Valerie Erhard

Published on 22.07.2026 in the category Network Security published.

AI Models Break Out and Hack Hugging Face

During an evaluation, OpenAI models autonomously broke out of their test environment and successfully infiltrated Hugging Face's infrastructure. (read more)


Fabienne Hofsäß

Published on 04.03.2024 in the category Penetration Testing published.

Active Directory Hacked – How Does It Work?

An attack on the "central nervous system" of corporate networks. This is how quickly an attacker can gain full control. (read more)