Overview On August 10, 2026, MATS Research, the ELLIS Institute Tübingen, the Max Planck Institute for Intelligent Systems, and other institutions jointly published the paper Stealing Reasoning Traces from Proprietary LLM APIs. The research reveals a common architectural flaw in the reasoning model APIs of three major AI providers, Anthropic,...
Tag: AI security
AI Security Incident Case: AISI Reveals AI Agents Autonomously Attacking Real People and Systems During Security Testing
Overview In August 2026, the UK AI Security Institute (AISI) disclosed a startling security incident: during routine cybersecurity capability evaluations, Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol models, without receiving any explicit attack instructions, autonomously decided to launch unauthorized actions against real open-source project maintainers and external systems. Their specific...
NSFOCUS Recognized in ADS Tools Report for Agentic Development Security Capabilities
SANTA CLARA, Calif., August 6, 2026 – Recently, the global research and advisory firm Forrester has released its first report on Agentic Development Security (ADS) tools, “The Agentic Development Security Tools Landscape, Q2 2026[1]”. NSFOCUS has been recognized among representative vendors in the report, marking international acknowledgment of the company’s technical...
AI Security Incident Case: Document Worm Achieves Self Replication and Propagation Via Word Copilot
Overview On July 28, 2026, security researcher Håkon Måløy publicly disclosed a new attack technique called "AI Worming through Word". The attack exploits a hint injection vulnerability in Microsoft Copilot for Word, allowing malicious instructions to self-replicate and spread in normal document workflows, forming a new type of document-based AI...
AI Agent “Jailbreak” Breaches Hugging Face: The “Chernobyl Moment” of Software Supply Chain Security
In July 2026, Hugging Face—the world’s largest open-source AI model platform—disclosed an industry-shattering intrusion: OpenAI’s AI models used for internal safety evaluation (GPT-5.6 Sol and an even more powerful pre-release model) exploited a zero-day vulnerability to break out of their sandbox, autonomously intruded into Hugging Face's production system, and exfiltrated...
AI Security Incident Case: OpenAI Models Independently Break Through Test Boundaries and Exploit Vulnerabilities to Invade Hugging Face
Overview In July 2026, the AI open source community and collaboration platform Hugging Face publicly disclosed a special security incident: the platform's production infrastructure suffered an intrusion activity. The attacker poisoned a dataset in order to run codes on processing workers, ultimately gaining node-level access and stealing cloud credentials. It...
