Tag: malicious
-
LayerX Exposes Critical Flaw in OpenAI’s ChatGPT Atlas Browser
LayerX found a flaw in ChatGPT’s Atlas browser letting hackers inject malicious code and exploit AI memory for remote access. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/news/openai-atlas-vulnerability/
-
Copilot diagrams could leak corporate emails via indirect prompt injection
The bigger threat of indirect prompt injection: The incident underscores that the risk goes beyond simple “prompt injection,” where a user types malicious instructions directly into an AI. Here, the attacker hides instructions inside document content that gets passed into the assistant without the user’s awareness. Logue described how the hidden instructions use progressive task…
-
Copilot diagrams could leak corporate emails via indirect prompt injection
The bigger threat of indirect prompt injection: The incident underscores that the risk goes beyond simple “prompt injection,” where a user types malicious instructions directly into an AI. Here, the attacker hides instructions inside document content that gets passed into the assistant without the user’s awareness. Logue described how the hidden instructions use progressive task…
-
Gamaredon Phishing Campaign Exploits WinRAR Vulnerability to Target Government Agencies
Tags: attack, cve, cyber, cybersecurity, exploit, government, group, malicious, phishing, software, threat, vulnerabilityCybersecurity researchers have uncovered a sophisticated phishing campaign orchestrated by the notorious Gamaredon threat group, specifically targeting government entities through exploitation of a critical WinRAR vulnerability. The attack leverages CVE-2025-8088, a path traversal vulnerability in the popular file compression software, to deliver weaponized RAR archives that silently deploy malicious payloads without requiring user interaction beyond…
-
OpenAI Atlas Browser Vulnerability Lets Attackers Execute Malicious Scripts in ChatGPT
Cybersecurity firm LayerX has identified a critical vulnerability in OpenAI’s ChatGPT Atlas browser that allows malicious actors to inject harmful instructions into ChatGPT’s memory and execute remote code. This security flaw poses significant risks to users across all browsers but presents particularly severe dangers for those using the new ChatGPT Atlas browser. Cross-Site Request Forgery…
-
New ChatGPT Atlas Browser Exploit Lets Attackers Plant Persistent Hidden Commands
Tags: access, ai, chatgpt, cybersecurity, exploit, intelligence, malicious, malware, openai, vulnerabilityCybersecurity researchers have discovered a new vulnerability in OpenAI’s ChatGPT Atlas web browser that could allow malicious actors to inject nefarious instructions into the artificial intelligence (AI)-powered assistant’s memory and run arbitrary code.”This exploit can allow attackers to infect systems with malicious code, grant themselves access privileges, or deploy malware,” LayerX First seen on thehackernews.com…
-
Crafted URLs can trick OpenAI Atlas into running dangerous commands
Attackers can trick OpenAI Atlas browser via prompt injection, treating malicious instructions disguised as URLs in the omnibox as trusted commands. Attackers can exploit the OpenAI Atlas browser by disguising malicious instructions as URLs in the omnibox, which Atlas interprets as trusted commands, enabling harmful actions. NeuralTrust researchers warn that agentic browsers fail by not…
-
Critical Chrome 0-Day Under Attack: Mem3nt0 Mori Hackers Actively Exploiting Vulnerability
In March 2025, security researchers at Kaspersky detected a sophisticated campaign exploiting a previously unknown Chrome vulnerability to deliver advanced spyware to high-profile targets. The attack, dubbed Operation ForumTroll, leveraged personalized phishing links to compromise organizations across Russia, including media outlets, universities, research centers, government agencies, and financial institutions. A single click on a malicious…
-
ChatGPT’s Atlas Browser Jailbroken to Hide Malicious Prompts Inside URLs
Security researchers at NeuralTrust have uncovered a critical vulnerability in OpenAI’s Atlas browser that allows attackers to bypass safety measures by disguising malicious instructions as innocent-looking web addresses. The flaw exploits how the browser’s omnibox interprets user input, potentially enabling harmful actions without proper security checks. The Omnibox Vulnerability Explained Atlas features an omnibox that…
-
ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands
The newly released OpenAI Atlas web browser has been found to be susceptible to a prompt injection attack where its omnibox can be jailbroken by disguising a malicious prompt as a seemingly harmless URL to visit.”The omnibox (combined address/search bar) interprets input either as a URL to navigate to, or as a natural-language command to…
-
ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands
The newly released OpenAI Atlas web browser has been found to be susceptible to a prompt injection attack where its omnibox can be jailbroken by disguising a malicious prompt as a seemingly harmless URL to visit.”The omnibox (combined address/search bar) interprets input either as a URL to navigate to, or as a natural-language command to…
-
Critical CoPhish Exploit Uses Copilot Studio to Hijack OAuth Tokens
Security researchers at Datadog have uncovered a sophisticated phishing technique that weaponizes Microsoft Copilot Studio to conduct OAuth token theft attacks. Dubbed >>CoPhish,
-
North Korean Chollima Actors Added BeaverTail and OtterCookie to its Arsenal
Famous Chollima, a DPRK-aligned threat group, has evolved its arsenal, with BeaverTail and OtterCookie increasingly merging functionalities to steal credentials and cryptocurrency via deceptive job offers. A recent campaign involved a trojanized Node.js application distributed through a malicious NPM package, highlighting the group’s adaptation in delivery methods. In the campaign, Famous Chollima notes merged BeaverTail…
-
706,000+ BIND 9 DNS Resolvers Exposed to Cache Poisoning PoC Released
A critical vulnerability affecting more than 706,000 BIND 9 DNS resolvers worldwide has been disclosed with proof-of-concept exploit code now publicly available. The security flaw enables attackers to perform cache poisoning attacks by injecting malicious DNS records into vulnerable resolver caches, potentially redirecting users to attacker-controlled infrastructure. The vulnerability, tracked as CVE-2025-40778, was disclosed by…
-
Hidden in Plain Sight: How we followed one malicious extension to uncover a multi-extension”¦
Hidden in Plain Sight: How we followed one malicious extension to uncover a multi-extension campaign Short read for everyone: we found a malicious Chrome extension that stole login data from a crypto trading site. Tracing the domain it talked to uncovered a second malicious extension. That second extension’s public metadata contained the developer email, which…
-
Hackers Exploit WordPress Arbitrary Installation Vulnerabilities in the Wild
Tags: control, cyber, cybersecurity, exploit, flaw, hacker, malicious, software, vulnerability, wordpressCybersecurity firm Wordfence has uncovered a renewed wave of mass exploitation targeting critical vulnerabilities in two popular WordPress plugins, allowing unauthenticated attackers to install malicious software and potentially seize control of websites. The flaws, first disclosed in late 2024, affect GutenKit and Hunk Companion plugins, which boast over 40,000 and 8,000 active installations respectively. Despite…
-
Top 10 Best Bug Bounty Platforms in 2025
As digital attack surfaces expand with rapid innovation in cloud, AI, and Web3 technologies, organizations increasingly rely on the collective intelligence of ethical hackers to identify vulnerabilities before malicious actors can exploit them. These platforms facilitate a structured, incentivized approach to security testing, offering unparalleled scalability, diversity of expertise, and cost-effectiveness compared to traditional security…
-
Smishing Triad Linked to 194,000 Malicious Domains in Global Phishing Operation
The threat actors behind a large-scale, ongoing smishing campaign have been attributed to more than 194,000 malicious domains since January 1, 2024, targeting a broad range of services across the world, according to new findings from Palo Alto Networks Unit 42.”Although these domains are registered through a Hong Kong-based registrar and use Chinese nameservers, the…
-
Cybersecurity Snapshot: Top Advice for Detecting and Preventing AI Attacks, and for Securing AI Systems
Tags: access, ai, attack, authentication, awareness, best-practice, breach, business, chatgpt, china, ciso, cloud, computing, container, control, credentials, crime, cve, cyber, cyberattack, cybersecurity, data, defense, detection, email, exploit, extortion, finance, flaw, framework, fraud, google, governance, government, group, guide, hacker, hacking, healthcare, iam, identity, incident response, intelligence, LLM, malicious, malware, mitigation, monitoring, network, open-source, openai, organized, phishing, ransom, risk, risk-management, russia, sans, scam, service, skills, soc, strategy, supply-chain, technology, theft, threat, tool, training, vulnerability, zero-trustAs organizations eagerly adopt AI, cybersecurity teams are racing to protect these new systems. In this special edition of the Cybersecurity Snapshot, we round up some of the best recent guidance on how to fend off AI attacks, and on how to safeguard your AI systems. Key takeaways Developers are getting new playbooks from groups…
-
Cross Site Scripting
Web applications are integral to modern business and online operations, but they can be vulnerable to security threats. Cross-Site Scripting (XSS) is a common vulnerability where attackers inject malicious scripts into trusted websites, compromising user data and website integrity. At StrongBox IT, we help organizations identify and mitigate such vulnerabilities, focusing on detecting and preventing……
-
Vault Viper Exploits Online Gambling Websites Using Custom Browser to Install Malicious Program
Tags: access, crime, cyber, cybersecurity, exploit, group, infrastructure, malicious, software, threatA major cybersecurity investigation has uncovered a sophisticated criminal operation called Vault Viper that exploits online gambling platforms to distribute a malicious custom browser with remote access capabilities. The threat actor, linked to the Baoying Group and connected to the Suncity Group”, a major Asian crime syndicate”, has created an unprecedented infrastructure combining iGaming software…
-
New PDF Tool Detects Malicious Files Using PDF Object Hashing
Proofpoint has released a new open-source tool called PDF Object Hashing that helps security teams detect and track malicious files distributed as PDFs. The tool is now available on GitHub and represents a significant advancement in identifying suspicious documents used by threat actors in phishing campaigns, malware distribution, and business email compromise attacks. PDFs have…
-
IIS Servers Hijacked via Exposed ASP.NET Machine Keys, Malicious Modules Injected in the Wild
Security researchers have uncovered a sophisticated cyberattack campaign that exploited publicly exposed ASP.NET machine keys to compromise hundreds of Internet Information Services (IIS) servers worldwide. The operation, detected in late August and early September 2025, deployed a previously undocumented malicious module dubbed >>HijackServer
-
IIS Servers Hijacked via Exposed ASP.NET Machine Keys, Malicious Modules Injected in the Wild
Security researchers have uncovered a sophisticated cyberattack campaign that exploited publicly exposed ASP.NET machine keys to compromise hundreds of Internet Information Services (IIS) servers worldwide. The operation, detected in late August and early September 2025, deployed a previously undocumented malicious module dubbed >>HijackServer
-
IIS Servers Hijacked via Exposed ASP.NET Machine Keys, Malicious Modules Injected in the Wild
Security researchers have uncovered a sophisticated cyberattack campaign that exploited publicly exposed ASP.NET machine keys to compromise hundreds of Internet Information Services (IIS) servers worldwide. The operation, detected in late August and early September 2025, deployed a previously undocumented malicious module dubbed >>HijackServer
-
3,000 YouTube Videos Exposed as Malware Traps in Massive Ghost Network Operation
A malicious network of YouTube accounts has been observed publishing and promoting videos that lead to malware downloads, essentially abusing the popularity and trust associated with the video hosting platform for propagating malicious payloads.Active since 2021, the network has published more than 3,000 malicious videos to date, with the volume of such videos tripling since…
-
Phishing Campaign Uses Unique UUIDs to Evade Secure Email Gateways
A sophisticated new phishing attack discovered in early February 2025 is successfully bypassing Secure Email Gateways (SEGs) and evading perimeter defenses through an ingenious combination of random domain selection, dynamic UUID generation, and browser session manipulation. The attack leverages a highly specialized JavaScript embedded in malicious attachments and spoofed cloud collaboration platforms, making it exceptionally…