Search results for ChatGPT security bypass | Breaking Cybersecurity News | The Hacker News

Medieval castles stood as impregnable fortresses for centuries, thanks to their meticulous design. Fast forward to the digital age, and this medieval wisdom still echoes in cybersecurity. Like castles with strategic layouts to withstand attacks, the Defense-in-Depth strategy is the modern counterpart — a multi-layered approach with strategic redundancy and a blend of passive and active security controls.  However, the evolving cyber threat landscape can challenge even the most fortified defenses. Despite the widespread adoption of the Defense-in-Depth strategy, cyber threats persist. Fortunately, the Defense-in-Depth strategy can be augmented using Breach and Attack Simulation (BAS), an automated tool that assesses and improves every security control in each layer. Defense-in-Depth: False Sense of Security with Layers Also known as multi-layered defense, the defense-in-depth strategy has been widely adopted by organizations since the early 2000s. It’s based on the assumption th...

Cybersecurity researchers have disclosed a zero-click flaw in OpenAI ChatGPT's Deep Research agent that could allow an attacker to leak sensitive Gmail inbox data with a single crafted email without any user action. The new class of attack has been codenamed ShadowLeak by Radware. Following responsible disclosure on June 18, 2025, the issue was addressed by OpenAI in early August. "The attack utilizes an indirect prompt injection that can be hidden in email HTML (tiny fonts, white-on-white text, layout tricks) so the user never notices the commands, but the agent still reads and obeys them," security researchers Zvika Babo, Gabi Nakibly, and Maor Uziel said . "Unlike prior research that relied on client-side image rendering to trigger the leak, this attack leaks data directly from OpenAI's cloud infrastructure, making it invisible to local or enterprise defenses." Launched by OpenAI in February 2025, Deep Research is an agentic capability built into ...

A high-severity security flaw has been disclosed in Meta's Llama large language model (LLM) framework that, if successfully exploited, could allow an attacker to execute arbitrary code on the llama-stack inference server.  The vulnerability, tracked as CVE-2024-50050 , has been assigned a CVSS score of 6.3 out of 10.0. Supply chain security firm Snyk, on the other hand, has assigned it a critical severity rating of 9.3. "Affected versions of meta-llama are vulnerable to deserialization of untrusted data, meaning that an attacker can execute arbitrary code by sending malicious data that is deserialized," Oligo Security researcher Avi Lumelsky said in an analysis earlier this week. The shortcoming, per the cloud security company, resides in a component called Llama Stack , which defines a set of API interfaces for artificial intelligence (AI) application development, including using Meta's own Llama models. Specifically, it has to do with a remote code execution ...

DALL-E for coders? That’s the promise behind vibe coding, a term describing the use of natural language to create software. While this ushers in a new era of AI-generated code, it introduces "silent killer" vulnerabilities: exploitable flaws that evade traditional security tools despite perfect test performance. A detailed analysis of secure vibe coding practices is available here . TL;DR: Secure Vibe Coding Vibe coding, using natural language to generate software with AI, is revolutionizing development in 2025. But while it accelerates prototyping and democratizes coding, it also introduces “silent killer” vulnerabilities: exploitable flaws that pass tests but evade traditional security tools. This article explores: Real-world examples of AI-generated code in production Shocking stats: 40% higher secret exposure in AI-assisted repos Why LLMs omit security unless explicitly prompted Secure prompting techniques and tool comparisons (GPT-4, Claude, Cursor, etc.) Reg...

As SaaS and cloud-native work reshape the enterprise, the web browser has emerged as the new endpoint. However, unlike endpoints, browsers remain mostly unmonitored, despite being responsible for more than 70% of modern malware attacks . Keep Aware’s recent State of Browser Security report highlights major concerns security leaders face with employees using the web browser for most of their work. The reality is that traditional security tools are blind to what happens within the browser , and attackers know it. Key Findings: 70% of phishing campaigns impersonate Microsoft, OneDrive, or Office 365 to exploit user trust. 150+ trusted platforms like Google Docs and Dropbox are being abused to host phishing and exfiltrate data. 10% of AI prompts involve sensitive business content, posing risks across thousands of browser-based AI tools. 34% of file uploads on company devices go to personal accounts, often undetected. New Attack Patterns Bypass Traditional Defenses From phis...

As 2025 draws to a close, security professionals face a sobering realization: the traditional playbook for web security has become dangerously obsolete. AI-powered attacks, evolving injection techniques, and supply chain compromises affecting hundreds of thousands of websites forced a fundamental rethink of defensive strategies. Here are the five threats that reshaped web security this year, and why the lessons learned will define digital protection for years to come. 1. Vibe Coding Natural language coding, " vibe coding " , transformed from novelty to production reality in 2025, with nearly 25% of Y Combinator startups using AI to build core codebases. One developer launched a multiplayer flight simulator in under three hours, eventually scaling it to 89,000 players and generating thousands in monthly revenue. The Result Code that functions perfectly yet contains exploitable flaws, bypassing traditional security tools. AI generates what you ask for, not what you forget...

Introduction Cyber threats targeting supply chains have become a growing concern for businesses across industries. As companies continue to expand their reliance on third-party vendors, cloud-based services, and global logistics networks, cybercriminals are exploiting vulnerabilities within these interconnected systems to launch attacks. By first infiltrating a third-party vendor with undetected security gaps, attackers can establish a foothold, leveraging these weaknesses to penetrate the primary business partners’ network. From there, they move laterally through critical systems, ultimately gaining access to sensitive data, financial assets, intellectual property, or even operational controls. Recent high-profile breaches like the 2024 ransomware attack that hit Change Healthcare, one of the world’s largest health payment processing companies, demonstrate how attackers disrupted supply chain operations stealing up to 6TB of millions of patients’ protected health information (PHI)....

A new attack campaign has targeted known Chrome browser extensions, leading to at least 35 extensions being compromised and exposing over 2.6 million users to data exposure and credential theft. The attack targeted publishers of browser extensions on the Chrome Web Store via a phishing campaign and used their access permissions to insert malicious code into legitimate extensions in order to steal cookies and user access tokens. The first company to shed light the campaign was cybersecurity firm Cyberhaven, one of whose employees was targeted by a phishing attack on December 24, allowing the threat actors to publish a malicious version of the extension. On December 27, Cyberhaven disclosed that a threat actor compromised its browser extension and injected malicious code to communicate with an external command-and-control (C&C) server located on the domain cyberhavenext[.]pro, download additional configuration files, and exfiltrate user data. The phishing email, which purported...

Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI's ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users' memories and chat histories without their knowledge. The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI's GPT-4o and GPT-5 models. OpenAI has since addressed some of them .  These issues expose the AI system to indirect prompt injection attacks , allowing an attacker to manipulate the expected behavior of a large language model (LLM) and trick it into performing unintended or malicious actions, security researchers Moshe Bernstein and Liv Matan said in a report shared with The Hacker News. The identified shortcomings are listed below - Indirect prompt injection vulnerability via trusted sites in Browsing Context, which involves asking ChatGPT to summarize the contents of web pages with malicious instructions added...

A new campaign named GhostPoster has leveraged logo files associated with 17 Mozilla Firefox browser add-ons to embed malicious JavaScript code designed to hijack affiliate links, inject tracking code, and commit click and ad fraud. The extensions have been collectively downloaded over 50,000 times, according to Koi Security, which discovered the campaign. The add-ons are no longer available. These browser programs were advertised as VPNs, screenshot utilities, ad blockers, and unofficial versions of Google Translate. The oldest add-on, Dark Mode, was published on October 25, 2024, offering the ability to enable a dark theme for all websites. The full list of the browser add-ons is below - Free VPN Screenshot Weather (weather-best-forecast) Mouse Gesture (crxMouse) Cache - Fast site loader Free MP3 Downloader Google Translate (google-translate-right-clicks) Traductor de Google Global VPN - Free Forever Dark Reader Dark Mode Translator - Google Bing Baidu DeepL Weather...

"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...

Cybersecurity researchers have disclosed a now-patched critical security flaw in a popular vibe coding platform called Base44 that could allow unauthorized access to private applications built by its users. "The vulnerability we discovered was remarkably simple to exploit -- by providing only a non-secret 'app_id' value to undocumented registration and email verification endpoints, an attacker could have created a verified account for private applications on their platform," cloud security firm Wiz said in a report shared with The Hacker News. A net result of this issue is that it bypasses all authentication controls, including Single Sign-On (SSO) protections, granting full access to all the private applications and data contained within them. Following responsible disclosure on July 9, 2025, an official fix was rolled out by Wix, which owns Base44, within 24 hours. There is no evidence that the issue was ever maliciously exploited in the wild. While vibe codin...