Zero-Click | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have uncovered a jailbreak technique to bypass ethical guardrails erected by OpenAI in its latest large language model (LLM) GPT-5 and produce illicit instructions. Generative artificial intelligence (AI) security platform NeuralTrust said it combined a known technique called Echo Chamber with narrative-driven steering to trick the model into producing undesirable responses. "We use Echo Chamber to seed and reinforce a subtly poisonous conversational context, then guide the model with low-salience storytelling that avoids explicit intent signaling," security researcher Martí Jordà said . "This combination nudges the model toward the objective while minimizing triggerable refusal cues." Echo Chamber is a jailbreak approach that was detailed by the company back in June 2025 as a way to deceive an LLM into generating responses to prohibited topics using indirect references, semantic steering, and multi-step inference. In recent weeks, the...

Cybersecurity researchers have disclosed a series of now-patched security vulnerabilities in Apple's AirPlay protocol that, if successfully exploited, could enable an attacker to take over susceptible devices supporting the proprietary wireless technology. The shortcomings have been collectively codenamed AirBorne by Israeli cybersecurity company Oligo. "These vulnerabilities can be chained by attackers to potentially take control of devices that support AirPlay – including both Apple devices and third-party devices that leverage the AirPlay SDK," security researchers Uri Katz, Avi Lumelsky, and Gal Elbaz said . Some of the vulnerabilities, like CVE-2025-24252 and CVE-2025-24132, can be strung together to fashion a wormable zero-click RCE exploit, enabling bad actors to deploy malware that propagates to devices on any local network the infected device connects to. This could then pave the way for sophisticated attacks that can lead to the deployment of backdoors an...