Results for “Microsoft”

TechCrunch AI Zack Whittaker SI

Chinese hackers spied on thousands of companies after breaching IT giant ConnectWise

Microsoft points the blame for ConnectWise's breach at a China-aligned hacker, which relied on AI agents to rapidly hack into thousands of its customers.

Read at TechCrunch AI

TechCrunch Startups Tim De Chant Startups

Fusion startup Helion is developing new semiconductors that could double output of its power plants

Helion now has another $225 million to help speed development of its first fusion power plant, due to provide Microsoft with electricity in 2028.

Read at TechCrunch Startups

Infosecurity Magazine Security

Microsoft: Chinese State Actor Used AI to Compromise ConnectWise Tenants

Microsoft said it has observed threat actor activity in multiple ConnectWise customer environments, with the attackers leveraging the ARTEX agentic AI platform

Read at Infosecurity Magazine

GeekWire Kurt Schlosser SI

Ex-Marine and Microsoft vets launch Watchtower Labs with $35M to bring AI to military logistics

The Bellevue-based defense tech startup, co-founded by a former Marine special operations officer and two longtime Microsoft engineering leaders, is building AI and simulation software to help military planners anticipate logistics needs.

Read at GeekWire

GeekWire Kurt Schlosser

Steve Ballmer’s USAFacts pits Ben Shapiro against Scott Galloway in YouTube debate special

With the former Microsoft CEO running the "Fact Desk," the debate centered on whether free markets or government policies are better equipped to preserve the American Dream amid a growing cost-of-living crisis.

Read at GeekWire

Google Project Zero James Forshaw Security

Windows Exploitation Techniques: Dangling COM Object Registrations

This short blog post is about abusing a privilege escalation bug that Microsoft recently fixed in Windows, CVE-2026-66804, that I and 14 others reported. This issue is an incomplete fix for CVE-2026-50343, a bug dubbed “Dark Elevator” by Calif. The root cause of the bug was a dangling COM object registration for the CrossDevice COM object with the CLSID {E9F83CF2-E0C0-4CA7-AF01-E90C70BEF496}. A COM registration typically needs two parts: a server executable, which for…

Read at Google Project Zero

Hacker News fourfire SI

ASCII smuggling crosses over from AI prompt injection to phishing evasion

Article URL: https://www.microsoft.com/en-us/security/blog/2026/09/03/ascii-smuggling-crosses-over-from-ai-prompt-injection-to-phishing-evasion/ Comments URL: https://news.ycombinator.com/item?id=49604092 Points: 1 # Comments: 0

Read at Hacker News

Simon Willison SI

AI Worming through Word

AI Worming through Word Neat new prompt injection variant by Håkon Måløy, who found a way to upgrade prompt injection attacks against Microsoft Word to full self-replicating worms: An attacker places hidden instructions in a document that is later used as source material in Copilot for Word. Copilot may interpret those instructions as part of the user’s request, causing it to manipulate the document being drafted or edited. Copilot may then also copy the hidden instructions…

Read at Simon Willison

Simon Willison SI

Microsoft Copilot Cowork Exfiltrates Files

Microsoft Copilot Cowork Exfiltrates Files The biggest challenge in designing agentic systems continues to be preventing them from enabling attackers to exfiltrate data. In this case Microsoft Copilot Cowork (yes, that's a real product name) was allowing agents to send emails to the user's own inbox without approval... but those messages were then displayed in a way that could leak data to an attacker via rendered images: Because these messages can contain external images…

Read at Simon Willison

arXiv (research papers) Dongcheng Zhang SI

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose…

Read at arXiv (research papers)

arXiv (research papers) Darren Cheng SI

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark (Greshake et al., 2024) against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense combines two mechanisms: agent isolation, implemented as a privilege separated two-agent pipeline with tool partitioning, and JSON formatting, which produces structured output that…

Read at arXiv (research papers)