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.
Varonis reported the flaw to Google in late 2025 and it has been addressed, but it reminds defenders to take a fresh look at their AI Infrastructure security.
An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt other systems.
Adversaries could plant a malicious repository that can execute arbitrary code and steal cloud credentials by exploiting the vulnerability, which showcases growing MCP risk.
Two separate campaigns target CVE-2025-8088, fixed last July, to conduct data theft and cyberespionage against military and government targets in Ukraine.
Flaws in OpenEMR's platform — used by more than 100,000 healthcare providers — enabled database compromise, remote code execution, and data theft.
A prompt injection vulnerability paired with other flaws can turn a Google search into a full attack chain that could threaten enterprise networks.
A new around of vulnerabilities in the popular AI automation platform could let attackers hijack servers and steal credentials.
A threat actor is leveraging a flaw in the Ray framework to hijack AI infrastructure worldwide and distribute a self-propagating cryptomining and data theft botnet.
CVE-2025-54603 gave attackers an opening to disrupt critical operational technology (OT) environments and steal data from them.
The flaws in the company's Triton Inference Server enables model theft, data leaks, and response manipulation.
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
Now a zero-day, the vulnerability enables NTLM hash theft, an issue that Microsoft has already fixed twice before.
Several of the flaws enable remote code execution and denial-of-service attacks while others enable data theft, session hijacking, and other malicious activity.
A prompt injection flaw in the AI feature of the workforce collaboration suite makes malicious queries of data sources appear legitimate.
The two MIT graduates discovered a flaw in a common trading tool for the Ethereum blockchain. Does it presage problems ahead for cryptocurrency?
The flaw poses a significant risk of unauthorized data access, system alterations, potential data theft, and complete takeover of vulnerable systems, especially in the IoT and embedded computing space.
Attackers continued to favor software exploits, phishing, and stolen credentials as initial-access methods last year, as Log4j and the Russia-Ukraine cyber conflict changed the threat landscape.
Unpatched Cisco bugs, tracked as CVE-2023-20025 and CVE-2023-20026, allow lateral movement, data theft, and malware infestations.
The group has been operating for over a year, promoting their tools in hacking forums, stealing credit card information, and using typosquatting techniques to target open source software flaws.