Bit2Watt is a newly disclosed cyber‑physical attack class that weaponizes AI and GPU workloads in modern data centers to destabilize nearby power grids, turning compute infrastructure itself into a grid‑scale threat surface. Measurements on NVIDIA acce…

A newly proposed framework argues that AI penetration testing must move beyond conventional infrastructure compromise and assess whether an adversary can make an AI-enabled system act against its intended operational purpose. Traditional penetration te…

OpenAI has introduced GPT-Red, an automated safety red-teaming model trained to identify and exploit prompt injection weaknesses in AI agents. Prompt injection occurs when malicious instructions hidden in webpages, emails, local files, code repositorie…

AI agents are increasingly crossing the line from generating content to executing actions inside developer workstations, cloud environments, and enterprise systems. New telemetry from Gen’s H1 2026 Threat Report shows that agent runtime controls detect…

Armored Likho, a previously undocumented threat group also tracked as Eagle Werewolf based on circumstantial evidence, is targeting government institutions and electric-power organizations across Russia, Brazil, and Kazakhstan with a new Python-based i…

Researchers have revealed a technique called “GhostCommit,” which involves prompt injection by hiding malicious instructions within images included in pull requests. This technique has the potential to bypass text-only AI code reviewers and…