Code Defender

Security researchers at Anthropic and Switzerland’s EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence (AI) agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions.

The work, released as a preprint on August 10, 2026, tests the technique in a simulated six-agent coding

A ransomware affiliate calling itself Ransom Busters has been spotted proactively sending emails to victim organizations and claims to delete stolen data from ransomware groups’ servers in exchange for a fee ranging from $20,000 to $60,000.

“In these messages, the third-party offers to help the victim recover from ransomware attack. This immediately stands out as anomalous,” GuidePoint Research

Two critical vulnerabilities impacting MLflow, an open-source artificial intelligence (AI) platform, and FUXA, an open-source, web-based SCADA / HMI software built for operational technology (OT) and industrial automation, are witnessing malicious scanning and exploitation efforts.

According to independent reports from watchTowr and VulnCheck, the vulnerabilities in question are as follows –

Varonis Threat Labs has disclosed three vulnerabilities in Microsoft Copilot Personal that it said could allow a single click on a crafted link to silently pull data from connected apps and other information available to the victim’s Copilot session.

The flaws, which the researchers collectively named CoSnitch, turn in part on an undocumented URL parameter that the assistant itself surfaced

The agency said the latest attack came amid preparations to select a manager for seized corporate rights in IDS Ukraine, one of the country’s largest producers of bottled mineral water and beverages.

The University of Texas at San Antonio, which serves 40,000 students across six campuses, said its IT team identified threat activity on its academic campus over the weekend and took some systems, including phones, offline in response.

The affected ministries — one responsible for urban development, construction and housing, and the other for mobility, transport, climate protection and the environment — have been isolated from government networks since Friday as a precaution.

The Cybersecurity and Infrastructure Security Agency (CISA) and FBI updated an advisory on the group initially released in March 2025 — writing that as of April 2026, Medusa actors have hit more than 500 victims. CISA previously said 300 victims, many of which are in critical infrastructure sectors, were attacked as of 2025.

Hackers stole names, addresses, phone numbers, Social Security numbers, and financial information from a third-party platform.

The post Heights Finance Data Breach Impacts at Least 1.2 Million Individuals appeared first on SecurityWeek.

Fortinet will use Virtue AI technology to enhance its AI security portfolio, including for AI models, applications, and agentic systems.

The post Fortinet Acquires AI Security Company Virtue AI appeared first on SecurityWeek.