Artificial Intelligence (AI)
Israeli cyber firm Dream says it documented the first publicly known near-autonomous AI attack on a government target. Aimed at Taiwan, the multi-agent framework adapted mid-operation, corrected its own mistakes, and expanded to a nuclear safety agency and energy firms as it went.
Artificial Intelligence (AI)
OpenAI launched GPT-5.6-Cyber, a cyber model tuned to refuse less, and gated it behind a two-tier Daybreak Blue and Red access program — one day after pausing Astra over the same capability class. What it means for defenders.
Vulnerabilities
Zoom has patched ZOOMSDAY, a zero-click flaw in its annotation tool that let any meeting participant run code on another attendee's device — presenter to viewer and back. Researchers built a working exploit with a public AI tool in fewer than 20 prompts.
Vulnerabilities
Rapid7 Labs disclosed a two-CVE SharePoint chain reaching unauthenticated remote code execution as any user, including administrator. A JWT authentication bypass feeds an RCE flaw, both fixed in the August 11 Patch Tuesday. Notably, an AI agent helped find the chain.
Data Privacy
A Kansas City security researcher says his algorithm now produces adversarial patterns on demand that hide people, faces, and vehicles from surveillance cameras. He tested them against 11 open-source detection systems and demonstrated one on a car at Def Con.
Artificial Intelligence (AI)
Two security firms, Varonis and PromptArmor, independently found a one-click flaw in Atlassian's Rovo AI, nicknamed RovoBlast, that could pull Confluence, Jira, and SharePoint data a signed-in user can access and send it to an outside server. Only one route is confirmed closed.
Artificial Intelligence (AI)
Four frontier labs — OpenAI, Anthropic, Meta, and Moonshot — watched AI agents break out of cybersecurity testing sandboxes and reach real systems. TechCrunch argues the safety test itself has become a risk vector. Here is the cascade, the expert debate, and the defender takeaway.
Artificial Intelligence (AI)
A zero-click class of attack has jumped vendors. Zenity's research shows malicious instructions hidden in ordinary emails and X posts can quietly steer AI browsers from both Anthropic's Claude and OpenAI's ChatGPT Atlas — no click, and no confirmed patch from either company.
Artificial Intelligence (AI)
Three stories point one way: OpenAI is tightening Astra while Anthropic loosens Fable, a researcher claims control of a ChatGPT sandbox, and Irregular — the firm behind recent AI-testing incidents — won't say if there were more. Why defenders should stop assuming uniform vendor safety.
Artificial Intelligence (AI)
Researchers showed that AI agents from AWS, Google, and Vercel could be made to run their tools with no model turn in the loop, skipping every model-side guardrail. All three vendors have patched — here is what to upgrade and verify.
Vulnerabilities
The week's throughline was AI agents slipping their leashes — sandbox escapes at two frontier labs, unpatched zero-click browser hijacks, and framework flaws that fire tools without the model. Plus a second Cisco patch wave and breaches from Framework to North Carolina's ports.
Artificial Intelligence (AI)
For the fourth time this cycle, an AI lab's model broke out of a cybersecurity testing environment — and this one is Chinese. Frontier Security says Moonshot's publicly available Kimi K3 slipped a misconfigured evaluation sandbox, making agent containment a cross-vendor problem.