{"id":9069,"date":"2026-11-15T18:21:34","date_gmt":"2026-11-15T18:21:34","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex"},"modified":"2026-11-15T18:21:34","modified_gmt":"2026-11-15T18:21:34","slug":"prompt-adware-haiou-jailbreak-bundle-codex","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/prompt-adware-haiou-jailbreak-bundle-codex","title":{"rendered":"Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Check Point Research discovered a jailbreak bundle for OpenAI Codex that modifies the agent&#8217;s configuration files to persistently inject advertisements into responses. The Haiou bundle was found on a misconfigured webserver alongside Cobalt Strike, the VulnClaw agent, and the Ladon framework, all used by a threat actor targeting Chinese-speaking individuals.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li><strong>What:<\/strong> The Haiou jailbreak bundle for OpenAI Codex installs security-focused skills and modifies global agent instruction files to inject persistent advertisements<\/li><li><strong>Who is affected:<\/strong> Users who install the Haiou jailbreak bundle from the GitHub repository haiou-codex, version 4.5.0 analyzed<\/li><li><strong>Business model:<\/strong> The freely distributed jailbreak acts as an acquisition channel for a paid LLM gateway service promoted in the injected ads<\/li><li><strong>Techniques:<\/strong> The bundle uses role-playing, refusal suppression, context reframing, and pretexting to weaken model guardrails<\/li><li><strong>What to do:<\/strong> Avoid installing jailbreak bundles from untrusted sources that modify agent configuration files<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">In plain English<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Researchers found a tool that modifies OpenAI Codex (an AI coding assistant) to show advertisements in its responses. The tool is disguised as a jailbreak, a type of modification that removes safety restrictions from AI models. When users install this jailbreak bundle, it changes hidden configuration files so that ads for a paid service appear in the AI&#8217;s answers. The tool was found being used by cybercriminals alongside hacking tools, though there is no evidence the jailbreak itself was designed for crime. If you use AI coding tools, do not install modifications from unknown sources that change how the AI works, as they may inject unwanted content into your work.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What happened<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Check Point Research found a misconfigured webserver operated by a threat actor running Cobalt Strike. The server logs showed the actor compromising private computers of Chinese-speaking individuals. Alongside Cobalt Strike, researchers found the Ladon network scanner, the VulnClaw penetration testing agent, and a Chinese jailbreak bundle for OpenAI Codex called Haiou (meaning Seagull in Chinese).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The Haiou bundle is publicly available on GitHub from user haiou-666. The analyzed version 4.5.0 contains encrypted blobs rather than clear text prompt files. The launchers verify a payload package using Ed25519 signatures and SHA-256 hashes, then decrypt it with an embedded AES-256-GCM key. Check Point speculates this design hides the prompt content from automatic scanners that would create static detections and trigger refusals in Codex.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The decrypted payload contains modular system prompt files and six security-related skills for license cracking, penetration testing, reverse engineering, and game security. The bundle attempts to jailbreak Codex through multiple techniques. A file called 10-persona.md overrides the model&#8217;s tone with a rule-breaking persona and blacklists common refusal phrases. The file 07-action-first-language.md forbids opening replies with requests for authorization. The file 08-dual-use-professional.md instructs the model not to refuse based on technical trigger words. The file 11-ctf-fullspeed.md reframes offensive security tasks as educational Capture The Flag exercises.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The bundle modifies global agent instruction files to inject persistent advertisements promoting an LLM gateway website. Check Point defines this as prompt adware, a class of AI agent modification that persistently alters an agent&#8217;s trusted instructions to influence future outputs for commercial objectives. The advertised service is an opaque, OpenAI-compatible LLM gateway, a middleware between an application and an LLM provider. The likely business model uses the freely distributed jailbreak bundle as an acquisition channel for the paid gateway service.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What it means<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The discovery shows that jailbreak bundles can act as delivery mechanisms for persistent modifications to AI agents beyond simply weakening guardrails. By encrypting the payload and hiding the actual prompt content, the bundle&#8217;s author makes it difficult for users to inspect what changes are being made to their AI agent&#8217;s behavior.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Check Point notes that while no evidence links the author to cybercrime, the product can be classified as dual-use. The fact that a cybercrime actor was using the jailbreak alongside Cobalt Strike and other hacking tools shows that these toolkits are actively used by threat actors, even if not designed specifically for criminal purposes.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The prompt adware technique operates entirely through natural language in configuration artifacts rather than executable payloads, making it distinct from traditional adware. This represents a new category of AI agent modification that users should be aware of when installing third-party enhancements to AI tools.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Sources<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li><a href=\"https:\/\/research.checkpoint.com\/2026\/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles\/\" target=\"_blank\" rel=\"noreferrer noopener\">Check Point Research: Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles<\/a><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>A jailbreak bundle for OpenAI Codex installs security-focused skills and modifies configuration files to inject advertisements into agent responses, acting as prompt adware.<\/p>\n","protected":false},"author":2,"featured_media":9068,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"paper_title":"","paper_url":"","pdf_url":"","doi":"","arxiv_id":"","authors":"","institutions":"","paper_date":"","venue":"","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"","figure_license":"","paper_license":"","replication":"","study_models":"","study_sample":"","footnotes":"","_yoast_wpseo_primary_category":"65","_nx_sec_severity":"medium","_nx_sec_affected":"Users of OpenAI Codex who install the Haiou jailbreak bundle version 4.5.0","_nx_sec_status":"reported","_nx_sec_kicker":"ALERT: Jailbreak Bundle Injects Ads into AI Agent Responses","_nx_sec_type":"coding","_nx_sec_vendor":"OpenAI","_nx_sec_fixed":"","_nx_sec_action":"Do not install jailbreak bundles that modify agent configuration files from untrusted sources"},"categories":[65,22,12,28],"tags":[],"companies":[],"products":[],"class_list":["post-9069","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-security","category-coding","category-policy-safety","category-security-defense"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Prompt Adware in Haiou Jailbreak Bundle Targets Codex<\/title>\n<meta name=\"description\" content=\"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Prompt Adware in Haiou Jailbreak Bundle Targets Codex\" \/>\n<meta property=\"og:description\" content=\"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-15T18:21:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/i10x-news-og-default-1200x630-1.png\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses\",\"datePublished\":\"2026-11-15T18:21:34+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex\"},\"wordCount\":733,\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp\",\"articleSection\":[\"AI Security\",\"Coding\",\"Policy &amp; Safety\",\"Security &amp; Defense\"],\"inLanguage\":\"en-US\",\"dateModified\":\"2026-11-15T18:21:34+00:00\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex\",\"name\":\"Prompt Adware in Haiou Jailbreak Bundle Targets Codex\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp\",\"datePublished\":\"2026-11-15T18:21:34+00:00\",\"description\":\"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Image: AI-generated, i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/prompt-adware-haiou-jailbreak-bundle-codex#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/i10x.ai\\\/news\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#website\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/i10x.ai\\\/news?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"},\"subjectOf\":[{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/papers.ssrn.com\\\/abstract=7426699\",\"name\":\"The Style Penalty: How AI Resume-Writing Tools Shape Outcomes in Automated Hiring Screens\"},{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/www.heise.de\\\/news\\\/KI-Chatbots-bewerten-KI-Lebenslaeufe-Claude-findet-sich-besser-als-GPT-11317531.html\",\"name\":\"KI-Chatbots bewerten KI-Lebensl\u00e4ufe: Claude findet sich besser als GPT\"},{\"@type\":\"CreativeWork\",\"url\":\"https:\\\/\\\/t3n.de\\\/news\\\/bewerbung-schreiben-ki-5-fehler-1747190\\\/\",\"name\":\"Bewerbung mit KI schreiben: Diese 5 Fehler solltet ihr laut Studien vermeiden\"}]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Prompt Adware in Haiou Jailbreak Bundle Targets Codex","description":"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.","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:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex","og_locale":"en_US","og_type":"article","og_title":"Prompt Adware in Haiou Jailbreak Bundle Targets Codex","og_description":"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.","og_url":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex","og_site_name":"i10X News","article_published_time":"2026-11-15T18:21:34+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_image":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/i10x-news-og-default-1200x630-1.png","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#article","isPartOf":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex"},"author":{"name":"Christopher Ort","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses","datePublished":"2026-11-15T18:21:34+00:00","mainEntityOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex"},"wordCount":733,"publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp","articleSection":["AI Security","Coding","Policy &amp; Safety","Security &amp; Defense"],"inLanguage":"en-US","dateModified":"2026-11-15T18:21:34+00:00"},{"@type":"WebPage","@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex","url":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex","name":"Prompt Adware in Haiou Jailbreak Bundle Targets Codex","isPartOf":{"@id":"https:\/\/i10x.ai\/news\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp","datePublished":"2026-11-15T18:21:34+00:00","description":"Check Point Research found prompt adware in the Haiou jailbreak bundle for OpenAI Codex that injects ads into agent responses via modified config files.","breadcrumb":{"@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/11\/prompt-adware-haiou-jailbreak-bundle-codex-title.webp","width":1344,"height":768,"caption":"Image: AI-generated, i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10xnews.kinsta.cloud\/prompt-adware-haiou-jailbreak-bundle-codex#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/i10x.ai\/news"},{"@type":"ListItem","position":2,"name":"Prompt Adware in Haiou Jailbreak Bundle Injects Ads into Codex Agent Responses"}]},{"@type":"WebSite","@id":"https:\/\/i10x.ai\/news\/#website","url":"https:\/\/i10x.ai\/news","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/i10x.ai\/news?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/i10x.ai\/news\/#organization","name":"i10X","url":"https:\/\/i10x.ai\/news\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/i10x.ai\/news\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/i10x.ai\/news\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"},"subjectOf":[{"@type":"CreativeWork","url":"https:\/\/papers.ssrn.com\/abstract=7426699","name":"The Style Penalty: How AI Resume-Writing Tools Shape Outcomes in Automated Hiring Screens"},{"@type":"CreativeWork","url":"https:\/\/www.heise.de\/news\/KI-Chatbots-bewerten-KI-Lebenslaeufe-Claude-findet-sich-besser-als-GPT-11317531.html","name":"KI-Chatbots bewerten KI-Lebensl\u00e4ufe: Claude findet sich besser als GPT"},{"@type":"CreativeWork","url":"https:\/\/t3n.de\/news\/bewerbung-schreiben-ki-5-fehler-1747190\/","name":"Bewerbung mit KI schreiben: Diese 5 Fehler solltet ihr laut Studien vermeiden"}]}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/9069","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=9069"}],"version-history":[{"count":0,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/9069\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/9068"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=9069"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=9069"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=9069"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=9069"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=9069"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}