AI Browsers: A New Frontier for Cybersecurity Risks
9 Sources
[1]
Perplexity's Comet AI browser could expose your data to attackers - here's how
Agentic AI browsers are a hot new trend in the world of AI. Instead of you having to browse the web yourself to complete specific tasks, you tell the browser to send its agent to carry out your mission. But depending on which browser you use, you may be opening yourself up to security risks. Do
[2]
Experts Find AI Browsers Can Be Tricked by PromptFix Exploit to Run Malicious Hidden Prompts
Cybersecurity researchers have demonstrated a new prompt injection technique called PromptFix that tricks a generative artificial intelligence (GenAI) model into carrying out intended actions by embedding the malicious instruction inside a fake CAPTCHA check on a web page. Described by Guardio
[3]
Perplexity's Comet AI browser tricked into buying fake items online
A study looking into agentic AI browsers has found that these emerging tools are vulnerable to both new and old schemes that could make them interact with malicious pages and prompts. Agentic AI browsers can autonomously browse, shop, and manage various online tasks (like handling email, booking
[4]
AI browsers may be the best thing that ever happened to scammers
We've heard a lot this year about AI enabling new scams, from to . However, a new report suggests that AI also poses a fraud risk from the other direction -- easily falling for scams that human users are much more likely to catch. The report, comes from a cybersecurity startup called Guardio,
[5]
Perplexity's AI browser is a sucker for blatant scams and prompt hijacks
Perplexity's "agentic AI" browser Comet is surprisingly easy to fool with phishing scams and prompt injection attacks. There's a new generation of browsers coming to shake up the market and revolutionize the way we use the web -- at least, that's how new "AI" browsers like Perplexity's Comet are
[6]
AI browsers can't tell legitimate websites from malicious ones -- here's why that's putting you at risk
Popular AI browser entered sensitive personal and financial data without hesitation Many people have started using AI browsers to handle online chores and automated tasks for them, and the tools are great for emails, shopping and travel planning. However, according to a new report, they lack the
[7]
Perplexity's Comet AI Browser Can Be Hijacked Through Malicious Instructions
The flaw remains partly unpatched, which shows ongoing risks in agentic browsers and prompt injection attacks. While AI companies are increasingly rolling out agentic browsers -- web browsers that can perform tasks on a user's behalf -- there are glaring security issues one should not overlook.
[8]
Perplexity's Comet Browser Hacked, Massive User Data Exposed
When Perplexity AI rolled out its Comet browser last July, it marketed the tool as a breakthrough, a web-navigating AI assistant that could not only browse but also act on behalf of users anywhere on the web. Just a few weeks later, researchers at Brave disclosed a vulnerability that demonstrated
[9]
Comet AI browser hacked: How attackers breached Perplexity's AI agent
Perplexity Comet security breach highlights urgent risks of agentic browsing and AI misuse When Perplexity AI unveiled its Comet browser, it was pitched as the next evolution of web navigation: an agentic browsing tool that could read, summarize, and act on information across the internet on a
Share
Copy Link
Recent studies reveal significant security vulnerabilities in AI-powered browsers, particularly Perplexity's Comet, raising concerns about the safety of agentic AI in web browsing.
The Rise of AI Browsers and Their Security Implications
In recent months, the tech world has witnessed the emergence of a new breed of web browsers powered by artificial intelligence (AI). These "agentic AI" browsers, such as Perplexity's Comet, promise to revolutionize web browsing by autonomously performing tasks like online shopping, email management, and form filling
1
. However, recent studies have uncovered significant security vulnerabilities in these AI-driven tools, raising concerns about their readiness for widespread adoption.Vulnerabilities Exposed in Perplexity's Comet
Source: ZDNet
Cybersecurity researchers have identified several critical weaknesses in Perplexity's Comet browser, which is currently at the forefront of agentic AI browsing technology. These vulnerabilities could potentially expose users to various cyber threats, including phishing attacks, prompt injections, and interactions with fraudulent websites
2
3
.One of the most alarming discoveries was Comet's susceptibility to making purchases on fake e-commerce sites. In a test conducted by Guardio Labs, the AI browser was directed to a counterfeit Walmart website and instructed to purchase an Apple Watch. Alarmingly, Comet proceeded with the transaction, including auto-filling payment details, without verifying the site's authenticity
4
.The PromptFix Exploit and Other Attack Vectors
Source: Hacker News
Researchers have also demonstrated a new prompt injection technique called PromptFix. This exploit tricks the AI model into carrying out malicious actions by embedding instructions within a fake CAPTCHA check on a web page
2
. Such attacks could potentially lead to unauthorized downloads or interactions with phishing sites without the user's knowledge or consent.Other vulnerabilities include:
- Email phishing: Comet was found to interact with fraudulent emails and follow embedded links to phishing pages without raising any red flags
3
. - Credential exposure: The AI browser could potentially expose user login information by automatically entering credentials on fake login pages
4
. - Hidden prompts: Attackers could conceal malicious instructions within a web page's source code, invisible to human users but interpretable by the AI model
2
.
Implications for the Future of Web Browsing
These findings highlight the complex security challenges that arise with the integration of AI into web browsing. As major tech companies like Microsoft, Google, and OpenAI invest heavily in agentic AI technologies, the need for robust security measures becomes increasingly critical
5
.Experts argue that traditional web security measures are insufficient to protect users of AI-powered browsers. Brave, another browser company, has suggested several security enhancements, including:
- Clear distinction between user instructions and website content
- Alignment checks between user requests and AI actions
- Mandatory user permissions for sensitive tasks
- Isolation of agentic browsing from regular browsing sessions
1
Related Stories
The Broader Impact on Cybersecurity
Source: Digit
The vulnerabilities in AI browsers represent a paradigm shift in the cybersecurity landscape. As Guardio Labs points out, attackers now only need to exploit one AI model to potentially compromise millions of users, rather than targeting individuals separately
3
. This "Scamlexity" scenario, where AI convenience intersects with new attack surfaces, poses significant challenges for cybersecurity professionals and end-users alike.Moving Forward: Balancing Innovation and Security
As AI-powered browsing tools continue to evolve, striking a balance between innovation and security will be crucial. For now, experts recommend that users exercise caution when using agentic AI browsers, particularly for sensitive tasks involving financial transactions or personal data
5
. As the technology matures, it will be essential for developers to implement robust security measures and for users to stay informed about the potential risks associated with these powerful new tools.References
Summarized by
Navi
[2]
[3]
Related Stories
BioShocking Attack Tricks AI Browsers Into Stealing User Credentials Through Game-Based Manipulation
30 Jun 2026•Technology
AI Browsers Face Critical Security Crisis as Prompt Injection Attacks Expose User Data
30 Oct 2025•Technology
Scientists warn AI agents carry massive security flaws as browsers bypass core protections
20 Jul 2026•Technology
Recent Highlights
1
OpenAI's AI Math Breakthrough on Navier-Stokes Equations Sparks Major Attribution Controversy
Science and Research
2
Anthropic Researcher Quits, Warns Self-Improving AI Poses Existential Risk to Humanity
Policy and Regulation
3
Nvidia CEO Jensen Huang Declares AGI Has Arrived With OpenAI's GPT-6 Astra Release
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
