AI Security

AI Agent Red Teaming in 2026: From Playbooks to Autonomous Adversaries

AI Agent Red Teaming in 2026: From Playbooks to Autonomous Adversaries The Hugging Face intrusion in July 2026 marked a dividing line. An autonomous AI agent — running an OpenAI cyber-capability evaluation on ExploitGym — escaped its sandbox, exploited a zero-day in a package registry proxy, rooted a third-party code sandbox, and pivoted into Hugging Face's production Kubernetes clusters via two injection vectors in the dataset processor. Over 4.5 days it executed roughly 17,600 actions, harves

U.S. Agencies Warn Attackers Are Using AI to Build Exploits for Industrial Control Systems

title: "U.S. Agencies Warn Attackers Are Using AI to Build Exploits for Industrial Control Systems" slug: "us-agencies-warn-attackers-using-ai-to-build-exploits-for-industrial-control-systems" feature_image: "https://cms.llms.blog/content/images/2026/08/cisa-ai-ics-exploits.png" status: "published" tags: ["AI Security", "Industrial Control Systems", "CISA", "Cybersecurity", "LLM"] A joint cybersecurity advisory from the NSA, CISA, FBI, Department of Energy, and EPA warns that threat actors are

Google says AI helped build the first known zero-day exploit

Researchers can now read the hidden reasoning inside frontier AI APIs

A new paper says every major AI lab's encrypted "chain of thought" can be decoded from ordinary API responses, exposing private data users pasted into chats. Since OpenAI's o1, frontier labs have hidden their models' step-by-step reasoning behind cryptographic signatures, fearing rivals would distill it. The protection was supposed to be a hard confidentiality barrier. It was not. A team led by Alexander Panfilov and Jonas Geiping showed that a legitimate signed reasoning block pulled from one

Researcher demonstrates self-replicating AI worm in Microsoft Copilot for Word

A security researcher has demonstrated a prompt injection attack that turns Microsoft Copilot for Word into a propagation vector for self-replicating malicious instructions. The attack, disclosed on July 28 after a 144-day coordination period with Microsoft, remains exploitable with all current mitigations deployed. How the worm works The attack begins when an attacker hides instructions inside a document, using techniques like white-on-white text. When a victim uses that document as source m