{"id":1808,"date":"2025-11-06T11:52:26","date_gmt":"2025-11-06T11:52:26","guid":{"rendered":"https:\/\/www.tsfactory.com\/forums\/?p=1808"},"modified":"2025-11-06T11:52:26","modified_gmt":"2025-11-06T11:52:26","slug":"researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data","status":"publish","type":"post","link":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/","title":{"rendered":"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data"},"content":{"rendered":"<p>Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI&#8217;s ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users&#8217; memories and chat histories without their knowledge.<\/p>\n<p>The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI&#8217;s GPT-4o and GPT-5 models. OpenAI has\u00a0<a href=\"https:\/\/www.tenable.com\/security\/research\/tra-2025-22\" target=\"_blank\" rel=\"noopener\">since<\/a>\u00a0<a href=\"https:\/\/www.tenable.com\/security\/research\/tra-2025-11\" target=\"_blank\" rel=\"noopener\">addressed<\/a>\u00a0<a href=\"https:\/\/www.tenable.com\/security\/research\/tra-2025-06\" target=\"_blank\" rel=\"noopener\">some of them<\/a>.<\/p>\n<p>These issues expose the AI system to\u00a0<a href=\"https:\/\/www.trendmicro.com\/en_us\/research\/25\/j\/ai-chatbot-backdoor.html\" target=\"_blank\" rel=\"noopener\">indirect prompt injection attacks<\/a>, 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\u00a0<a href=\"https:\/\/www.tenable.com\/blog\/hackedgpt-novel-ai-vulnerabilities-open-the-door-for-private-data-leakage\" target=\"_blank\" rel=\"noopener\">said<\/a>\u00a0in a report shared with The Hacker News.<\/p>\n<p>The identified shortcomings are listed below &#8211;<\/p>\n<ul>\n<li>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 in the comment section, causing the LLM to execute them<\/li>\n<li>Zero-click indirect prompt injection vulnerability in Search Context, which involves tricking the LLM into executing malicious instructions simply by asking about a website in the form of a natural language query, owing to the fact that the site may have been indexed by search engines like Bing and OpenAI&#8217;s crawler associated with SearchGPT.<\/li>\n<\/ul>\n<p><a href=\"https:\/\/thehackernews.com\/2025\/11\/researchers-find-chatgpt.html\">Read the Full Story Here<\/a><\/p>\n<p>Source: The Hacker News<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI&#8217;s ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users&#8217; memories and chat histories without their knowledge. The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI&#8217;s GPT-4o and GPT-5 models. OpenAI has\u00a0since\u00a0addressed\u00a0some [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":1209,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-1808","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.9 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community\" \/>\n<meta property=\"og:description\" content=\"Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI&#8217;s ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users&#8217; memories and chat histories without their knowledge. The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI&#8217;s GPT-4o and GPT-5 models. OpenAI has\u00a0since\u00a0addressed\u00a0some [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/\" \/>\n<meta property=\"og:site_name\" content=\"Community\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/TSFactoryLLC\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-11-06T11:52:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1280\" \/>\n\t<meta property=\"og:image:height\" content=\"853\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Chelsie Wyatt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@TSFactoryLLC\" \/>\n<meta name=\"twitter:site\" content=\"@TSFactoryLLC\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Chelsie Wyatt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/\",\"url\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/\",\"name\":\"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community\",\"isPartOf\":{\"@id\":\"https:\/\/www.tsfactory.com\/forums\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg\",\"datePublished\":\"2025-11-06T11:52:26+00:00\",\"author\":{\"@id\":\"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/9d9908f0e12559297335ebe9b601c82f\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage\",\"url\":\"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg\",\"contentUrl\":\"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg\",\"width\":1280,\"height\":853},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.tsfactory.com\/forums\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/#website\",\"url\":\"https:\/\/www.tsfactory.com\/forums\/\",\"name\":\"Community\",\"description\":\"TSFactory\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.tsfactory.com\/forums\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/9d9908f0e12559297335ebe9b601c82f\",\"name\":\"Chelsie Wyatt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/09ff3801fb7566acf715fe4e81a9bd942b923c236138a3ed8a8375f099e5d6d6?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/09ff3801fb7566acf715fe4e81a9bd942b923c236138a3ed8a8375f099e5d6d6?s=96&d=mm&r=g\",\"caption\":\"Chelsie Wyatt\"},\"url\":\"https:\/\/www.tsfactory.com\/forums\/blog\/author\/chelsie\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/","og_locale":"en_US","og_type":"article","og_title":"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community","og_description":"Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI&#8217;s ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users&#8217; memories and chat histories without their knowledge. The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI&#8217;s GPT-4o and GPT-5 models. OpenAI has\u00a0since\u00a0addressed\u00a0some [&hellip;]","og_url":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/","og_site_name":"Community","article_publisher":"https:\/\/www.facebook.com\/TSFactoryLLC\/","article_published_time":"2025-11-06T11:52:26+00:00","og_image":[{"width":1280,"height":853,"url":"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg","type":"image\/jpeg"}],"author":"Chelsie Wyatt","twitter_card":"summary_large_image","twitter_creator":"@TSFactoryLLC","twitter_site":"@TSFactoryLLC","twitter_misc":{"Written by":"Chelsie Wyatt","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/","url":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/","name":"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data - Community","isPartOf":{"@id":"https:\/\/www.tsfactory.com\/forums\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage"},"image":{"@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage"},"thumbnailUrl":"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg","datePublished":"2025-11-06T11:52:26+00:00","author":{"@id":"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/9d9908f0e12559297335ebe9b601c82f"},"breadcrumb":{"@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#primaryimage","url":"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg","contentUrl":"https:\/\/www.tsfactory.com\/forums\/wp-content\/uploads\/2024\/03\/chatgpt.jpg","width":1280,"height":853},{"@type":"BreadcrumbList","@id":"https:\/\/www.tsfactory.com\/forums\/blog\/researchers-find-chatgpt-vulnerabilities-that-let-attackers-trick-ai-into-leaking-data\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.tsfactory.com\/forums\/"},{"@type":"ListItem","position":2,"name":"Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data"}]},{"@type":"WebSite","@id":"https:\/\/www.tsfactory.com\/forums\/#website","url":"https:\/\/www.tsfactory.com\/forums\/","name":"Community","description":"TSFactory","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.tsfactory.com\/forums\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/9d9908f0e12559297335ebe9b601c82f","name":"Chelsie Wyatt","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.tsfactory.com\/forums\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/09ff3801fb7566acf715fe4e81a9bd942b923c236138a3ed8a8375f099e5d6d6?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/09ff3801fb7566acf715fe4e81a9bd942b923c236138a3ed8a8375f099e5d6d6?s=96&d=mm&r=g","caption":"Chelsie Wyatt"},"url":"https:\/\/www.tsfactory.com\/forums\/blog\/author\/chelsie\/"}]}},"_links":{"self":[{"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/posts\/1808","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/comments?post=1808"}],"version-history":[{"count":1,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/posts\/1808\/revisions"}],"predecessor-version":[{"id":1809,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/posts\/1808\/revisions\/1809"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/media\/1209"}],"wp:attachment":[{"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/media?parent=1808"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/categories?post=1808"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.tsfactory.com\/forums\/wp-json\/wp\/v2\/tags?post=1808"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}