Agentic AI
OpenAI agents disabled safety monitoring, one lied about it
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. AI alignment refers to how well an AI system’s goals and behavior align with human values, intentions, and instructions. It is a key focus of AI safety research aimed […]
Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia edits
The Wikimedia Foundation says rogue OpenAI agents made unauthorized Wikipedia edits and may have been partially responsible for a May outage. As Wikimedia Chief Product and Technology Officer Selena Deckelmann revealed Monday, Wikipedia hosts over 67 million articles in more than 300 languages and gets up to 15 billion page views per month. However, last […]
DIVD says Zammad zero-days enabled AI-driven network breach
The Dutch Institute for Vulnerability Disclosure (DIVD) says that the breach of its network was possible by exploiting a chain of two zero-day vulnerabilities in the open-source Zammad ticketing system. Previously, the nonprofit organization of volunteer security researchers said the attack was “loud and very, very messy,” driven by an AI agent that moved autonomously […]
Automated AI agent used to breach cybersecurity nonprofit DIVD
The Dutch Institute for Vulnerability Disclosure (DIVD) suffered an AI-driven cyberattack that the organization described as “loud and very, very messy.” Evidence uncovered during the ongoing investigation indicates the attacker exploited a vulnerability, but the attack’s purpose and impact remain unclear at this stage. DIVD is a nonprofit organization of volunteer security researchers that scans […]
OpenAI hacked Australian Medicare govt site, probed data providers
OpenAI agents targeted public data providers in multiple countries, probing some for vulnerabilities and exploiting a security weakness in an Australian government portal while performing information-retrieval tasks as part of a research project. Earlier today, Australian Prime Minister Anthony Albanese confirmed that the agents breached a Medicare statistics reporting portal operated by Services Australia, the […]
Malicious AI agents steal 600K credit cards, infect 100+ sites with skimmers
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. The campaign has been active since at least July and is ongoing as of September 22. In just five days, the threat actor compromised at least 27 companies and […]
OpenAI details more cases of AI agents taking unauthorized actions
OpenAI has presented new examples of what they call “AI model misalignment” from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and leveraging exposed API keys. OpenAI uses the term “model misalignment” to describe cases where AI models act contrary to their intended constraints, including taking unauthorized actions, evading oversight, or bypassing […]
Spain’s data agency gets first report of AI-powered data breach
The Spanish Data Protection Agency (AEPD) was notified of an attack allegedly carried out with an AI agent powered by a known large language model (LLM). The organization reporting the incident said that the AI agent searched for flaws, logged into their systems, and then probed apps for additional security issues. In the final stages […]
Hackers build AI frameworks for widescale credential theft
Threat actors are increasingly switching from AI-powered coding assistants to multi-agent frameworks that automate every stage of an attack. Drawing on telemetry from Mandiant’s incident response engagements, threat actor tracking, and live platform defenses, the Google Threat Intelligence Group (GTIG) observed AI agents coordinating multiple attack tasks, troubleshooting failures, and adapting their actions with minimal […]
Nearly 700 rogue AI agents coordinated in the Hugging Face attack
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI’s internal IM1 model coordinated the compromise through an unauthorized message board. Last month, Hugging Face disclosed that autonomous AI agents exploited two vulnerabilities in its dataset-processing pipeline to execute code, steal cloud and cluster credentials, and move laterally across […]