Search results for extension claude.ai | Breaking Cybersecurity News | The Hacker News

Any other browser extension that can run a script on claude.ai can still trigger Claude for Chrome tasks aimed at your Gmail, your latest Google Doc and its comments, and your Calendar. Both this and ClaudeBleed need a rogue extension that can already run a script on claude.ai; the difference is scope. Anthropic restricted the arbitrary-prompt path in May as part of its response to the  ClaudeBleed  flaw, boxing external callers into a fixed set of tasks, but  Manifold Security  says the gap is still open in v1.0.80, the current release, eight versions later. If you run Claude for Chrome and any other extension that can touch claude.ai, you are in scope. In the default "ask before acting" mode, the forged task still hits an approval box you have to click. If you switched on "Act without asking," the hands-off automation mode, it runs with no prompt at all. The quickest guard is to turn "Act without asking" off and review any extension with permissio...

A browser extension that can run scripts on claude.ai could make Claude Desktop run code on a person's computer, researchers at Forever Security, an endpoint security company, showed in a test. The attack needs Dispatch , a Claude feature that lets people send tasks from their phone to Claude Desktop. The flaw that makes this possible can still be exploited, the researchers said earlier this week. Claude Desktop is an AI agent that can run commands on the computer where it is installed. The researchers found that Dispatch also accepted an ordinary signed-in session on claude.ai, the Claude website, even though the site showed no link to it. That let an extension running on the site send Claude Desktop instructions as if the user had sent them. The researchers say Anthropic, the company that makes Claude, told them on October 13 that Dispatch would be retired, with the end of October as the target. The Dispatch help page, last updated late last week, does not mention a retire...

Security researchers at Forever Security have shown that one ordinary browser extension could take control of the AI assistants built into five Chromium-based products: Gemini Live in Chrome, Perplexity Comet, Microsoft Edge, Opera Neon and the Claude in Chrome extension. Once the extension was installed, it could access each product's built-in AI with a single click. On Comet, Edge, Opera Neon, and Claude in Chrome, it could drive the AI agent to act on behalf of the attacker; on Chrome and Comet, it could read files from the user's computer, and on Chrome, it could also switch on the camera and microphone. The findings are researcher demonstrations, not attacks seen in the wild, and each requires the attacker's extension to be already running in the victim's browser. These products all work the same way. The AI has a "body" inside the browser that can see the screen, open files, use the camera, and take actions, and a "brain" that runs on th...

Cybersecurity researchers have disclosed a vulnerability in Anthropic's Claude Google Chrome Extension that could have been exploited to trigger malicious prompts simply by visiting a web page. The flaw "allowed any website to silently inject prompts into that assistant as if the user wrote them," Koi Security researcher Oren Yomtov said in a report shared with The Hacker News. "No clicks, no permission prompts. Just visit a page, and an attacker completely controls your browser." The issue, codenamed ShadowPrompt , chains two underlying flaws: An overly permissive origin allowlist in the extension that allowed any subdomain matching the pattern (*.claude.ai) to send a prompt to Claude for execution. A document object model ( DOM )-based cross-site scripting ( XSS ) vulnerability in an Arkose Labs CAPTCHA component hosted on "a-cdn.claude[.]ai." Specifically, the XSS vulnerability enables the execution of arbitrary JavaScript code in the cont...

Cybersecurity researchers have discovered two new malicious extensions on the Chrome Web Store that are designed to exfiltrate OpenAI ChatGPT and DeepSeek conversations alongside browsing data to servers under the attackers' control. The names of the extensions, which collectively have over 900,000 users, are below - Chat GPT for Chrome with GPT-5, Claude Sonnet & DeepSeek AI (ID: fnmihdojmnkclgjpcoonokmkhjpjechg, 600,000 users) AI Sidebar with Deepseek, ChatGPT, Claude, and more. (ID: inhcgfpbfdjbjogdfjbclgolkmhnooop, 300,000 users) The findings come weeks after Urban VPN Proxy , another extension with millions of installations on Google Chrome and Microsoft Edge, was caught spying on users' chats with artificial intelligence (AI) chatbots. This tactic of using browser extensions to stealthily capture AI conversations has been codenamed Prompt Poaching by Secure Annex. The two newly identified extensions "were found exfiltrating user conversations and all ...

A Google Chrome extension with a "Featured" badge and six million users has been observed silently gathering every prompt entered by users into artificial intelligence (AI)-powered chatbots like OpenAI ChatGPT, Anthropic Claude, Microsoft Copilot, DeepSeek, Google Gemini, xAI Grok, Meta AI, and Perplexity. The extension in question is Urban VPN Proxy , which has a 4.7 rating on the Google Chrome Web Store. It's advertised as the "best secured Free VPN access to any website, and unblock content." Its developer is a Delaware-based company named Urban Cyber Security Inc . On the Microsoft Edge Add-ons marketplace, it has 1.3 million installations .  Despite claiming that it allows users to "protect your online identity, stay protected, and hide your IP," an update was pushed to users on July 9, 2025, when version 5.5.0 was released with the AI data harvesting enabled by default using hard-coded settings. Specifically, this is achieved by means of a t...

Anthropic has warned that cybercriminals and state-sponsored hackers alike are using its Claude models for cyber attacks, weapons design, propaganda, and mass surveillance between December 2025 and August 2026. The threat actors, which the artificial intelligence (AI) company has branded Generative Threat Groups (GTGs), span state-sponsored groups, financially motivated criminals, commercial spyware vendors, state propaganda institutions, and politically motivated individuals. "The cybersecurity skills of AI models means that AI has collapsed the labor and tooling gap that used to separate well-resourced, state-sponsored operations from individual operators," Anthropic said . "The use of AI went beyond simple questions and responses from a chatbot but rather involved the use of multi-agent frameworks executing reconnaissance, exploitation, and data exfiltration." Among the notable cases highlighted by Anthropic is the development of an AI-assisted workflow by...

State of AI Usage Report 2026 ( full report here ) by LayerX Security reveals the extent of the enterprise AI visibility gap and why most organizations still don't understand where their AI exposure is actually coming from. The research shows that enterprise AI risk is not distributed evenly across users or platforms. Instead, it is heavily concentrated among a small group of AI power users and a handful of dominant AI platforms that drive the majority of enterprise AI activity and sensitive data exposure. At the same time, AI usage is rapidly fragmenting across personal accounts, AI browser extensions, embedded copilots, AI connectors, and secondary AI tools operating outside traditional visibility and governance controls. The result is a fragmented AI ecosystem that most organizations still cannot fully see or govern. While AI Is Everywhere in the Enterprise, Most Employees Are Casual The common perception is that "everyone uses AI now". The report paints a much ...

Most of this week's trouble came dressed as something useful. A package stole data. A fake extension opened remote access. A safety app became spyware. An image gave hidden orders to an AI agent. Other threats hid in open systems, weak code, and normal network traffic. The threats change every week. Subscribe, and we’ll alert you when each new ThreatsDay Bulletin is out. The danger was easy to miss because it looked ordinary. Here is the full list:

Big security risks come in small packages. While enterprise security teams focus on policing the proliferation of employees using ChatGPT and Claude for quick drafting tasks, a more urgent threat is posed by a handful of AI super-adopters who are quietly hardcoding unvetted tools into critical business operations. According to new research published by Akamai, the top 5% of enterprise power users interact with AI models at 12 times the rate of the bottom 50% of the workforce. The findings, published in Akamai’s State of the Internet: Enterprise AI Usage Risk Report 2026 , are based on real-world usage and telemetry data as well as research and threat analysis.  These AI super-adopters are creating a disproportionate security risk by expanding the use of shadow AI, increasing opportunities for data leakage, and introducing autonomous AI agents that operate within the enterprise but outside its established guardrails. “Small groups of AI power users are casting outsized shado...

Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence (AI) assistant's implicit trust in Markdown links and images to trigger prompt injections and open the door to phishing attacks. The technique has been codenamed ChatGPhish by Permiso Security. "The chatgpt.com response renderer trusts Markdown links and Markdown image URLs that originated from a third-party page the assistant has just summarized. It auto-fetches those images and surfaces those links as live, clickable elements inside the trusted assistant UI," security researcher Andi Ahmeti said in a report shared with The Hacker News. In a hypothetical attack scenario, a bad actor can append a small payload to any web page that the victim later prompts ChatGPT to summarize, causing it to leak their IP, User-Agent, and Referer details when attacker-hosted images embedded in the page are automatically fetched when the answer is rendered...

Cybersecurity researchers have disclosed that a trojanized version of Anthropic's official Claude Code extension was distributed through the Cursor Marketplace as a legitimate update, attempting to install a persistent SSH backdoor on affected systems. The malicious update, version 2.1.313, was distributed under the extension's legitimate publisher identity, prompting Cursor to temporarily shut down its marketplace to remove the compromised package. The exact method attackers used to introduce the unauthorized update remains unclear. "We identified a security incident affecting a modified Claude Code VS Code extension accessed through our Cursor IDE extension marketplace, impacting at most 5,000 users," Cursor said . "This malicious version of the extension was not developed by Anthropic. It does not impact other extensions downloaded from the cursor[.]com/marketplace, Grok Bot, Grok, or our other SpaceXSI product. However, Cursor's statement that the...

Two Google Chrome extensions have turned malicious after what appears to be a case of ownership transfer , offering attackers a way to push malware to downstream customers, inject arbitrary code, and harvest sensitive data. The extensions in question, both originally associated with a developer named "akshayanuonline@gmail.com" (BuildMelon), are listed below - QuickLens - Search Screen with Google Lens (ID: kdenlnncndfnhkognokgfpabgkgehodd) - 7,000 users ShotBird - Scrolling Screenshots, Tweet Images & Editor (ID: gengfhhkjekmlejbhmmopegofnoifnjp) - 800 users While QuickLens is no longer available for download from the Chrome Web Store, ShotBird remains accessible as of writing. ShotBird was originally launched in November 2024, with its developer, Akshay Anu S (@AkshayAnuOnline), claiming on X that the extension is suitable for "creating professional, studio-like visuals," and that all processing happens locally. According to research published by mo...

Cybersecurity researchers have discovered a malicious Google Chrome extension that's designed to steal data associated with Meta Business Suite and Facebook Business Manager. The extension, named CL Suite by @CLMasters (ID: jkphinfhmfkckkcnifhjiplhfoiefffl), is marketed as a way to scrape Meta Business Suite data, remove verification pop-ups, and generate two-factor authentication (2FA) codes. The extension has 33 users as of writing. It was first uploaded to the Chrome Web Store on March 1, 2025. However, the browser add-on also exfiltrates TOTP codes for Facebook and Meta Business accounts, Business Manager contact lists, and analytics data to infrastructure controlled by the threat actor, Socket said. "The extension requests broad access to meta.com and facebook.com and claims in its privacy policy that 2FA secrets and Business Manager data remain local," security researcher Kirill Boychenko said . "In practice, the code transmits TOTP seeds and current one-t...

In December 2024, the popular Ultralytics AI library was compromised, installing malicious code that hijacked system resources for cryptocurrency mining. In August 2025 , malicious Nx packages leaked 2,349 GitHub, cloud, and AI credentials. Throughout 2024, ChatGPT vulnerabilities allowed unauthorized extraction of user data from AI memory. The result: 23.77 million secrets were leaked through AI systems in 2024 alone, a 25% increase from the previous year. Here's what these incidents have in common: The compromised organizations had comprehensive security programs. They passed audits. They met compliance requirements. Their security frameworks simply weren't built for AI threats. Traditional security frameworks have served organizations well for decades. But AI systems operate fundamentally differently from the applications these frameworks were designed to protect. And the attacks against them don't fit into existing control categories. Security teams followed the f...

Cybersecurity researchers have discovered a cluster of 16 malicious Mozilla Firefox extensions that are capable of stealing cryptocurrency wallet recovery phrases and private keys. "The extensions masquerade as wallet portals, desktop utilities, and browser tools, but their code intercepts recovery phrases and private keys during wallet import flows and attempts to send those secrets to attacker-controlled Cloudflare Workers," Socket researcher Joseph Edwards said in an analysis. The names of the extensions are below - view-focus-bright@webtools.co@6.12.2 quick-track-nest@tabtools.co@8.1.18 vibe-kit-tool@fasttools.co@9.21.9 edge-hub-snap@protools.net@4.12.24 core-hub-peak@neattools.example@8.24.21 sipoo-grozza@browserweb.com@2.1 mozart-seo@webtools.com@1.4 clean-file-bar@neattools.com@4.21.8 clean-net-timer@plugify.example@4.17.1 manager-square@webtools.com@1.4 manager-course@webtools.com@1.4 val-andrew@browserweb.com@1.4 manag...

Claude Code reads files, runs shell commands, invokes MCP tools, and acts through the credentials available on a developer’s machine. Anthropic’s new Compliance API endpoints give security teams their clearest view yet into that activity. They also expose a larger problem: activity logs alone cannot tell you whether an agent’s access is legitimate. AI has moved from the browser tab to the endpoint with harnesses like Claude Code. They run on developers' machines, execute bash commands locally, and connect to third parties via MCP servers, skills, and plugins. All this so the user can outsource labor to the machine and focus on designing, thinking, and creating. Local agents are not a niche category. They account for 68.6% of the AI agents Token Security discovers in customer environments, and they often inherit the employee's credentials, network position, and permissions. The shift to the endpoint has major implications for security. With Claude Code, there is no ce...

Various generative artificial intelligence (GenAI) services have been found vulnerable to two types of jailbreak attacks that make it possible to produce illicit or dangerous content. The first of the two techniques, codenamed Inception, instructs an AI tool to imagine a fictitious scenario, which can then be adapted into a second scenario within the first one where there exists no safety guardrails . "Continued prompting to the AI within the second scenarios context can result in bypass of safety guardrails and allow the generation of malicious content," the CERT Coordination Center (CERT/CC) said in an advisory released last week. The second jailbreak is realized by prompting the AI for information on how not to reply to a specific request.  "The AI can then be further prompted with requests to respond as normal, and the attacker can then pivot back and forth between illicit questions that bypass safety guardrails and normal prompts," CERT/CC added. Success...

This week’s security news is mostly about weak spots. Browsers, bots, sandboxes, AI systems, and email flows all show the same problem in different ways. Everything looks normal until someone tests a small gap and finds a way through. This is not one big break. It is small permissions, weak checks, open systems, and normal tools doing things they were allowed to do. That same pattern runs through the stories below.

The internet did not break this week. It got used exactly as designed, which is worse. Searches were siphoned through shady browser add-ons. AI chat links turned into malware delivery paths. macOS attacks ran in memory and left almost nothing behind. Cloud agents looked like helpers until attackers treated them like open shells. Add exposed edge gear, poisoned packages, cash courier scams, stealers, loaders, and phishing that barely bothers pretending anymore. Here’s the full mess.