Overview In August 2026, Oasis Security disclosed a high-severity vulnerability in NVIDIA's NemoClaw framework (CVE-2026-65105, CVSS 3.1 score 8.1). The vulnerability allows an attacker to fully take over a locally running Ollama model service and implant persistent hidden instructions into the AI model via a single malicious webpage and without...
Tag: AI risk
AI Security Incident Case: Encrypted Reasoning Blocks of Proprietary LLMs Can Be Stolen via Cross-Model Replay
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,...
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...
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 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...
AI Security Incident Case: Ghostcommit Attack Leveraged Images to Steal Secrets
Overview On July 11, 2026, two researchers from the ASSET Research Group at the University of Missouri-Kansas City, Sudipta Chattopadhyay and Murali Ediga, disclosed a novel attack technique named Ghostcommit. This attack is capable of exfiltrating the entire contents of a target's .env file. The ingenuity of this attack lies...
