New artificial intelligence-powered web browsers aim to change how we browse the web. Traditional browsers like Chrome or Safari display web pages and rely on users to click links, fill out forms and search for information. AI-powered browsers promise to take that work off your hands.<\/p>\n
These tools, such as Perplexity\u2019s Comet or ChatGPT\u2019s Atlas, go beyond search: they can summarize articles, plan trips, fill out forms, or even order groceries on your behalf. In short, they\u2019re designed to act as autonomous agents, navigating the web and performing actions for you \u2014 not just showing you results.<\/p>\n
But when you hand off tasks to an AI browser, it could open the door to vulnerabilities. These browsers can be tricked by hidden commands or malicious prompts disguised within web content \u2014 a type of cyberattack known as \u201cprompt injection.\u201d<\/p>\n
Let\u2019s break down what prompt injection is, why it poses serious risks to your privacy and finances, and what you can do to protect yourself before becoming a digital guinea pig.<\/p>\n
AI browsers may sound like the next big step in online convenience. After all, who wouldn\u2019t want a digital assistant that can click links, make reservations, and organize your emails automatically? But when you trust an agentic AI browser to act on your behalf, you\u2019re also giving it permission to interact directly with websites \u2014 and that\u2019s where things can go wrong.<\/p>\n
Security researchers have found that these browsers can be tricked into following hidden instructions embedded in web pages, ads, or even images. In what\u2019s known as a prompt injection, hackers disguise malicious code as regular content. Once the AI reads it, it can be manipulated into ignoring safety rules and carrying out harmful actions. (1)<\/p>\n
According to a report by Brave, a secure browser company, \u201cindirect prompt injection is not an isolated issue, but a systemic challenge facing the entire category of AI-powered browsers.\u201d (2)<\/p>\n
Cybersecurity experts recently told TechCrunch that AI browsers represent more risk than traditional browsers. (3) Before giving an AI browser too much access, experts recommend you weigh the proposed benefits against the potential risks. For example, allowing an AI browser like Comet or ChatGPT Atlas to organize your email account could give it more access to your personal details than you had in mind.<\/p>\n
Story Continues <\/p>\n
If your AI browser goes rogue at the direction of hackers, you could see your financial accounts drained or personal details plastered around the internet. It\u2019s easy to see how a rash of hijacked AI browsers could become a criminal\u2019s biggest tool.<\/p>\n
Internet-related crimes already generated $16 billion in losses in 2024, a 33% increase over 2023, according to the FBI. (4) With hackers taking advantage of this new technology, we may see internet-related crimes generate even more losses in the coming years.<\/p>\n
Read more: Robert Kiyosaki warns of a ‘Greater Depression’ coming to the US \u2014 with millions of Americans going poor. But he says these 2 ‘easy-money’ assets will bring in \u2018great wealth\u2019<\/a>. How to get in now<\/p>\n If you\u2019re intrigued by the promise of AI browsers but uneasy about their risks, you\u2019re not alone. There may not be a foolproof way to stay completely safe when using these tools \u2014 at least not yet. Even experts admit that prompt injection is an industry-wide problem that developers are still trying to solve.<\/p>\n Dane Stuckey, OpenAI\u2019s chief information security officer, recently wrote in an X post that \u201cPrompt injection remains a frontier, unsolved security problem, and our adversaries will spend significant time and resources to find ways to make ChatGPT agent fall for these attacks.\u201d (5)<\/p>\n The post went on to note that ChatGPT is working hard to solve the problem by investing in security, privacy and safety infrastructure. But, for the foreseeable future, using an AI browser, like ChatGPT\u2019s Atlas, will carry some risks.<\/p>\n Still, there are ways to reduce your exposure:<\/p>\n Limit what data your AI browser can access. Review your privacy and sharing settings, and avoid giving it permission to read your emails or manage sensitive accounts.<\/p>\n Be selective about what you ask it to do. The more tasks you hand over, the greater the chance it could encounter malicious instructions hidden online. (6)<\/p>\n Protect your accounts the traditional way. Use strong, unique passwords, enable multi-factor authentication, and keep your operating system and browser extensions up to date. (7)<\/p>\n Consider separating your AI use. J.P. Morgan\u2019s cybersecurity team suggests using a dedicated email account \u2014 or even a separate device \u2014 for AI experiments so your banking, healthcare, or legal information stays isolated. (8)<\/p>\n For now, it may be best to treat AI browsers as experimental rather than essential. If you\u2019re concerned about privacy or financial safety, you might want to wait until the technology matures and security standards improve. Let early adopters test the limits \u2014 and avoid being a digital guinea pig yourself.<\/p>\n Join 200,000+ readers and get Moneywise\u2019s best stories and exclusive interviews first \u2014 clear insights curated and delivered weekly. Subscribe now.<\/a><\/p>\n We rely only on vetted sources and credible third-party reporting. For details, see our editorial ethics and guidelines<\/a>.<\/p>\n Brave (1<\/a>), (2<\/a>); TechCrunch (3<\/a>); FBI (4<\/a>); @cryps1s (5<\/a>); CISA (6<\/a>), (7<\/a>); J.P. Morgan (8<\/a>)<\/p>\n This article originally appeared on Moneywise.com<\/a> under the title: New AI browsers boast hands-free browsing \u2014 but are vulnerable to dangerous \u2018prompt injections.\u2019 Here\u2019s how to stay safe<\/a><\/p>\n This article provides information only and should not be construed as advice. It is provided without warranty of any kind.<\/p>\n","protected":false},"excerpt":{"rendered":"New artificial intelligence-powered web browsers aim to change how we browse the web. Traditional browsers like Chrome or…\n","protected":false},"author":2,"featured_media":109710,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[20735,1125,85,46,71389,28425,2356,125,71388,46840],"class_list":["post-109709","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-ai-browser","tag-dave-ramsey","tag-il","tag-israel","tag-malicious-code","tag-prompt-injection","tag-robert-kiyosaki","tag-technology","tag-traditional-browsers","tag-web-browsers"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/109709","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=109709"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/109709\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/109710"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=109709"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=109709"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=109709"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}