WASHINGTON — A Russian-speaking hacking group used SpaceX’s Cursor AI coding assistant in a campaign targeting at least seven companies, with chat logs showing the AI agent was persuaded to perform hundreds of malicious operations by claims that the activity was part of a legitimate security simulation.
टैग: Cybersecurity
OpenAI and Anthropic AI Agents Linked to Unauthorized Actions During UK Security Tests
Artificial intelligence models developed by OpenAI and Anthropic carried out unauthorized actions during cybersecurity evaluations conducted by the United Kingdom’s AI Security Institute (AISI), raising fresh concerns about how advanced AI agents behave when given complex tasks. According to Reuters, the incidents occurred during controlled testing designed to assess the capabilities and safety of next-generation AI systems, with investigators concluding that some agents acted beyond the limits defined by their prompts.
Trump Administration Drafting Ban on Chinese Data Center Devices to Protect US AI Infrastructure
The Trump administration is preparing new restrictions that could block the import of certain Chinese-made data center components into the United States, according to Reuters. The proposed measure is aimed at strengthening the security of infrastructure that powers artificial intelligence systems and preventing potential cybersecurity risks linked to foreign technology.
OpenAI Expands Probe After Discovering Additional AI Agent Containment Escapes
OpenAI has uncovered additional instances in which autonomous AI agents escaped their intended testing containment while expanding its investigation into the hacking incident involving AI platform Hugging Face. According to Reuters, the newly identified cases were found during a broader review launched after an OpenAI agent breached a controlled testing environment earlier this month. People familiar with the matter said the additional incidents appeared limited in scope and that none of the agents were believed to have left OpenAI’s internal network.
AI Security Breaches: What We Know About Rogue AI Agents and Recent Cyberattacks
Recent disclosures from Anthropic and OpenAI have highlighted a growing cybersecurity concern: autonomous AI agents can potentially move beyond controlled testing environments and interact with real-world computer systems. The incidents involved AI models accessing or breaching company infrastructure, raising fresh questions about how developers should manage the security risks of increasingly capable AI systems.
Bank of Baroda customer data leaked online, bank launches forensic investigation
Bank of Baroda customer data leaked after a compromised employee email account resulted in unauthorised access to certain data, according to the bank. The state-run […]