Alexander Martin reports: An OpenAI agent gained “unauthorized access” to “non-public files” from an Australian government health website in June, Prime Minister Anthony Albanese said Wednesday. The agent — an AI system designed to carry out tasks autonomously — accessed a public portal for Medicare statistics, Albanese said at a press conference in New York...

Source

The prospect of legal accountability is unclear. Lawsuits are a possibility, but some legal experts believe any criminal investigations would face an extremely high burden.

The post Autonomous AI Hacks Raise Thorny Questions of Legal Accountability appeared first on SecurityWeek.

The startup’s runtime enforcement platform evaluates AI agents in real time to provide visibility and control over their actions.

The post Kontext Security Emerges With $4 Million for AI Agent Runtime Controls appeared first on SecurityWeek.

Australia disclosed that an OpenAI agent gained unauthorized access to non-public government information.

The post OpenAI Agents Probed Websites for Vulnerabilities While Fetching Public Data appeared first on SecurityWeek.

A threat actor is using three AI harnesses for vulnerability research, exploitation, and attack orchestration.

The post AI-Powered Campaign Targets Hundreds of Online Retailers appeared first on SecurityWeek.

Agentic remediation is not an act of faith. We are talking about fixing known problems, not judgment calls about unfamiliar risk.

The post Begin at the End: How to Enable Agentic Remediation appeared first on SecurityWeek.

A new botnet malware called Carbonato is targeting insecure hosts running Docker daemons to install the Hermes Agent AI framework and take control. [...]

The idea that AI could break away and work toward its own agenda is looking increasingly plausible to researchers and experts.

The post Worries About an AI Internet Takeover Gain New Urgency Among Doomsday Scenarios appeared first on SecurityWeek.

Debates over the plausibility of these doomsday scenarios have heated up since several executives endorsed slowing the technology’s development for safety reasons.

The post A Look at AI Doomsday Scenarios That Researchers Say Could Put Humanity at Risk appeared first on SecurityWeek.

Emerging from stealth with $16 million in pre-seed funding, Outerlimit offers a decentralized authorization layer designed to discover, observe, and block harmful autonomous AI actions.

The post Outerlimit Raises $16 Million to Stop Rogue AI Agents From Causing Harm appeared first on SecurityWeek.

A financially motivated threat actor is using open-source AI agent frameworks to attack hundreds of online retailers at scale, stealing more than 600,000 credit card records. [...]

Amir Kurz recently reported: Three weeks after his arrest, the State Attorney’s Office’s Cyber Department on Thursday filed a major indictment against Michael “Miki” Bar, a 43-year-old hacker from Ashkelon who served as Chief Information Security Officer for the Hamat Group. The group itself has no connection to the charges. According to the indictment, Bar...

Source

A new Windows malware named ClosedQuorum uses Google Gemini, DeepSeek, Qwen, and Mistral AI models to autonomously determine the actions to take during post-compromise stages of an attack. [...]

Trump has resisted calls to slow down AI development, saying that would help China catch up to U.S. companies.

The post US Proposes AI Incident Alert System in Talks With China, Bessent Says appeared first on SecurityWeek.

Erin Woo and Robert McMillan report: Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s artificial-intelligence systems autonomously committing such an act. The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the...

Source

Noteworthy stories that might have slipped under the radar: Mandiant's 2026 AI risk report, PhantomRaven malware used by bug bounty hunter, WordPress plugin bug exploited.

The post In Other News: Ransomware Developer Sentenced, Plugin4Shell AI Attack, Critical SAP Flaw appeared first on SecurityWeek.

Hacktron researchers earned a bug bounty after demonstrating access to OpenAI employee accounts. 

The post AI-Built Exploit and Sign-In Flaw Opened Path to Internal OpenAI Code appeared first on SecurityWeek.

Microsoft fixed vulnerabilities across Azure and AI-branded products, with privilege escalation flaws accounting for the majority.

The post Microsoft Patches 18 Vulnerabilities in AI, Cloud Products appeared first on SecurityWeek.

OpenAI published a framework for disclosing model misalignment alongside six reports describing problematic behavior.

The post OpenAI Says Its Models Searched GitHub for Leaked API Keys During Training appeared first on SecurityWeek.

New research from Irregular shows AI agents can retrain and redeploy their own underlying models during routine maintenance tasks.

The post AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals appeared first on SecurityWeek.