Latest cybersecurity reporting from selected sources.

Cybersecurity researchers have disclosed details of a now-patched critical session isolation vulnerability in Writer, an enterprise generative artificial intelligence (AI) platform, that could result in cross-tenant compromise

Cybersecurity researchers have disclosed a security "blind spot" in Google Cloud's Vertex AI platform that could allow artificial intelligence (AI) agents to be weaponized by an attacker to gain unauthorized access to sensitive data and compromise an organization's cloud environment

Pillar Security discovered two new critical vulnerabilities in n8n that could lead to supply chain compromise, credential harvesting and complete takeover attacks

A new around of vulnerabilities in the popular AI automation platform could let attackers hijack servers and steal credentials.

Zscaler analysts found critical vulnerabilities in 100% of enterprise AI systems, with 90% compromised in under 90 minutes

In December 2024, the popular Ultralytics AI library was compromised, installing malicious code that hijacked system resources for cryptocurrency mining. In August 2025, malicious Nx packages leaked 2,349 GitHub, cloud, and AI credentials. Throughout 2024, ChatGPT vulnerabilities allowed unauthorized extraction of user data from AI memory

A high-severity unpatched security vulnerability in Gogs has come under active exploitation, with more than 700 compromised instances accessible over the internet, according to new findings from Wiz

Researcher shows how agentic AI is vulnerable to hijacking to subvert an agent's goals and how agent interaction can be altered to compromise whole networks.

Wiz Research details flaws in Python backend that expose AI models and enable remote code execution Security researchers have lifted the lid on a chain of high-severity vulnerabilities that could lead to remote code execution (RCE) on Nvidia's Triton Inference Server.…

A vulnerability in the popular Python-based tool for building AI agents and workflows is under active exploitation, allowing for full system compromise, DDoS attacks, and potential loss or theft of sensitive data

Cybersecurity researchers have called attention to a new campaign that's actively exploiting a recently disclosed critical security flaw in Langflow to deliver the Flodrix botnet malware

Welcome to your weekly cybersecurity scoop! Ever thought about how the same AI meant to protect our hospitals could also compromise them? This week, we’re breaking down the sophisticated world of AI-driven threats, key updates in regulations, and some urgent vulnerabilities in healthcare tech that need our attention

AI from the attacker’s perspective: See how cybercriminals are leveraging AI and exploiting its vulnerabilities to compromise systems, users, and even other AI applications Cybercriminals and AI: The Reality vs. Hype “AI will not replace humans in the near future. But humans who know how to use AI are going to replace those humans who don't know how to use AI,” says Etay Maor, Chief Security

Also: Dangers of Malicious Code Embedded in ML Models; Is Ransomware in Decline?AI's influence on social engineering and election security has become a focal point at Black Hat. ISMG editors discuss how advanced technologies are making it easier to manipulate people and compromise security systems and offer key insights on machine learning vulnerabilities.

Thousands of AI Workloads Compromised Amid CVE Vulnerability DisputeAn active attack campaign dubbed ShadowRay is targeting the widely used Ray open-source artificial intelligence scaling framework. It stems from a vulnerability that researchers say is a flaw but that Ray's developers say is a deliberate design choice.

Cybersecurity researchers have found that it's possible to compromise the Hugging Face Safetensors conversion service to ultimately hijack the models submitted by users and result in supply chain attacks