Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.
Search across headline titles and summaries.
Weekly headline count for the current query.
Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution
AutoJack is a novel exploit chain showing how a single malicious webpage can turn an AI browsing agent into a remote code execution vector on the host machine. By abusing trust in localhost, missing authentication, and unsafe parameter handling, attackers can trigger arbitrary process execution through AutoGen Studio’s MCP WebSocket. The research highlights a broader pattern - when agents can browse untrusted content and access local services, traditional boundaries like localhost are no longer secure. The post AutoJack: How a single page can RCE the host running your AI agent appeared first on Microsoft Security Blog.
Microsoft Patch Tuesday security updates for June 2026 fix a record 208 CVEs, including one actively exploited zero-day and multiple critical RCE flaws. Microsoft Patch Tuesday security updates for June 2026 mark a record. Microsoft shipped fixes for 208 CVEs across Windows, Office, Azure, Exchange, Hyper-V, Secure Boot, BitLocker, and a range of AI tooling. […]
Exposed UIs, weak authentication, and risky defaults could turn cloud-native AI apps on Kubernetes into potential targets by threat actors. Learn how exploitable misconfigurations lead to RCE and data leaks. The post When configuration becomes a vulnerability: Exploitable misconfigurations in AI apps appeared first on Microsoft Security Blog.
Also, HexDex Arrest, Black Axe Crackdown, LeRobot RCE FlawThis week, election threats resurfaced. A prolific hacker arrested. Black Axe network disrupted. China-linked disinformation targets Tibet. Exploited ScreenConnect and Windows flaws raise alarms. Minecraft gamers hit with stealer malware. A critical AI framework bug enables remote code execution.
Researchers found the popular model context protocol (MCP) servers, which are integral components of AI services, carry serious vulnerabilities.
Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence (AI) inference engines, including those from Meta, Nvidia, Microsoft, and open-source PyTorch projects such as vLLM and SGLang
A newly disclosed set of security flaws in NVIDIA's Triton Inference Server for Windows and Linux, an open-source platform for running artificial intelligence (AI) models at scale, could be exploited to take over susceptible servers