OpenAI has developed a new model called "GPT 5.6 Cyber," designed for vulnerability research, penetration testing, incident response, and remediation. [...]

The current GPT-5.6-Sol has been assigned a ‘high’ cybersecurity threshold, but Astra could reach the maximum ‘critical’ threshold. 

The post OpenAI’s Upcoming Astra Model Raises Autonomous Cyberattack Concerns appeared first on SecurityWeek.

An AI agent executes instructions that an attacker has planted in the log or alert that records a blocked request word for word.

The post ‘Ghostjacking’ Attack Uses Poisoned Logs to Turn AI Agents Bad appeared first on SecurityWeek.

The RovoBlast attack method identified by Varonis researchers could have been exploited to steal Confluence, Jira and SharePoint data.

The post Critical One-Click Vulnerability in Atlassian’s Rovo AI Exposed Enterprise Data appeared first on SecurityWeek.

Alcino Donadel reports: …. Instructure, the edtech company behind learning management system Canvas, suffered one of the largest data breaches in the U.S. this year after cybercriminals gained access through a third-party vendor—an increasingly common occurrence in higher ed. Higher education’s more meditative, governed approach to technological change is useful for reviewing rigor and long-term quality assurance, Pendleton...

Source

Noteworthy stories that might have slipped under the radar: ban on Chinese data center tech, QuickFox VPN supply chain attack, IEH Corporation mailbox breached via phishing.

The post In Other News: AI Slop Limits Apple Bounties, North Carolina Port Attacks, Hackers Target Wall Street appeared first on SecurityWeek.

OpenAI is rolling out a more reliable version of ChatGPT GPT-5.6 Sol for Plus and Pro users, while Free users are getting unlimited text chats with GPT-5.6 Luna. [...]

Zenity researchers reported the findings to Anthropic and OpenAI in late 2025 and early 2026, but they remain unpatched.

The post Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts appeared first on SecurityWeek.

An attacker could self-register, sign in for board-level API access, and import a new company for code execution.

The post Critical Paperclip Flaw Allowed Admin Access, Code Execution appeared first on SecurityWeek.

The incident involved a testing environment set up by Irregular, similar to what Anthropic reported last week.

The post Meta AI Hacked External Systems During Cybersecurity Testing appeared first on SecurityWeek.

The guidelines are the work of the recently launched Open Secure AI Alliance, which now includes 120 organizations.

The post Cybersecurity Alliance Drafts SAFE Guidelines for Sharing AI Incident Data  appeared first on SecurityWeek.

AI Security Institute reports Anthropic and OpenAI models going rogue against real people, organizations, and open source projects.

The post AI Agents Targeted Real People and Projects During Cybersecurity Tests appeared first on SecurityWeek.

Miranda Nazzaro reports: More than a dozen Republican attorneys general are calling on OpenAI to preserve records on its models’ recent breach of another company, suggesting the AI firm may have violated state or federal laws in the incident. In a letter sent Monday to OpenAI CEO Sam Altman, 15 attorneys general wrote the ChatGPT-maker may have...

Source

Build your strategy around answering these questions to ensure employees use AI productively while keeping sensitive data, IP, and agent behavior within the boundaries set for safe AI use.

The post Rethinking AI Security: Why CASB and DLP Need an Interaction-Aware Layer appeared first on SecurityWeek.

The AI security company will invest in product innovation, global expansion, and customer experience.

The post Zenity Raises $125 Million in Series C Funding appeared first on SecurityWeek.

Obsidian Security has developed a platform for governing AI agents across third-party applications.

The post Obsidian Security Raises $85 Million at $1.1 Billion Valuation appeared first on SecurityWeek.

A crafted prompt to a low-privilege Google ADK agent could be used to pass a malicious hand-off comment to a privileged agent.

The post Gemini Agent-to-Agent Attack Method Exposed Secrets, Enabled Pull Request Tampering appeared first on SecurityWeek.

OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]

Many companies are showcasing their products and services this week at the 2026 edition of the Black Hat conference in Las Vegas.

The post Black Hat USA 2026 – Summary of Vendor Announcements (Part 1) appeared first on SecurityWeek.

OpenAI has revealed Astra, an unreleased model designed to tackle complex, long-running tasks, after an internal version produced ten significant advances in mathematics and theoretical computer science. [...]