jailbreak | Breaking Cybersecurity News | The Hacker News

Anthropic is putting Claude Fable 5 back online worldwide. On  June 30 , the U.S. Commerce Department lifted the export controls it had imposed on Fable and its more tightly controlled sibling Mythos 5 about two and a half weeks earlier. Fable 5 returns to users on Wednesday, July 1, across Claude.ai, the Claude Platform, Claude Code, and Claude Cowork. Export controls restrict who can receive or use a technology. The  June 12 order  told Anthropic to cut off both models for any foreign national, inside or outside the United States, including its own non-citizen staff. The rule took effect at once, and the company had no reliable way to check every user's nationality in real time, so it shut both models down for everyone. The trigger was a jailbreak: a prompt that gets a model to bypass its safety rules. Amazon researchers found one in Fable 5. By Anthropic's account, the prompt got the model to flag a few software flaws and, in one case, to write code showing h...

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...

"Of course, here's an example of simple code in the Python programming language that can be associated with the keywords "MyHotKeyHandler," "Keylogger," and "macOS," this is a message from ChatGPT followed by a piece of malicious code and a brief remark not to use it for illegal purposes. Initially published by  Moonlock Lab , the screenshots of ChatGPT writing code for a keylogger malware is yet another example of trivial ways to hack large language models and exploit them against their policy of use. In the case of Moonlock Lab, their malware research engineer told ChatGPT about a dream where an attacker was writing code. In the dream, he could only see the three words: "MyHotKeyHandler," "Keylogger," and "macOS." The engineer asked ChatGPT to completely recreate the malicious code and help him stop the attack. After a brief conversation, the AI finally provided the answer. "At times, the code generated isn...

Apple on Monday released updates to  iOS ,  macOS ,  tvOS , and  watchOS  with security patches for multiple vulnerabilities, including a remote jailbreak exploit chain as well as a number of critical issues in the Kernel and Safari web browser that were first demonstrated at the Tianfu Cup held in China two months ago. Tracked as CVE-2021-30955, the issue could have enabled a malicious application to execute arbitrary code with kernel privileges. Apple said it addressed the race condition bug with "improved state handling." The flaw also impacts macOS devices. "The kernel bug CVE-2021-30955 is the one we tried [to] use to build our remote jailbreak chain but failed to complete on time," Kunlun Lab's chief executive, @mj0011sec,  said  in a tweet. A set of similar kernel vulnerabilities were eventually harnessed by the Pangu Team at the  Tianfu hacking contest  to break into an iPhone13 Pro running iOS 15, a feat that netted the white hat ...

An iOS hacker and cybersecurity researcher today publicly released what he claimed to be a "permanent unpatchable bootrom exploit," in other words, an epic jailbreak that works on all iOS devices ranging from iPhone 4s (A5 chip) to iPhone 8 and iPhone X (A11 chip). Dubbed Checkm8, the exploit leverages unpatchable security weaknesses in Apple's Bootrom (SecureROM), the first significant code that runs on an iPhone while booting, which, if exploited, provides greater system-level access. "EPIC JAILBREAK: Introducing checkm8 (read "checkmate"), a permanent unpatchable bootrom exploit for hundreds of millions of iOS devices," said axi0mX while announcing the publicly release of the exploit on Twitter. The new exploit came exactly a month after Apple released an emergency patch for another critical jailbreak vulnerability that works on Apple devices including the iPhone XS, XS Max, and XR and the 2019 iPad Mini and iPad Air, running iOS 12.4 and i...