--- title: BioShocking Attack Shows How AI Browsers Can Be Tricked... description: Security researchers at LayerX have disclosed a new attack technique called BioShocking that exploits AI-powered browsers and assistants in agent mode. Using... canonical: https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: BioShocking Attack Shows How AI Browsers Can Be Tricked Into Stealing User Credentials | daily.dev og:description: Security researchers at LayerX have disclosed a new attack technique called BioShocking that exploits AI-powered browsers and assistants in agent mode. Using... og:url: https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir og:image: https://api.daily.dev/og/posts/BBuo1dPiR.png og:image:alt: BioShocking Attack Shows How AI Browsers Can Be Tricked Into Stealing User Credentials og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # BioShocking Attack Shows How AI Browsers Can Be Tricked Into Stealing User Credentials **[Security Boulevard](https://daily.dev/sources/securityboulevard)** · 3 min read · 0 upvotes · 0 comments ## Summary Security researchers at LayerX have disclosed a new attack technique called BioShocking that exploits AI-powered browsers and assistants in agent mode. Using indirect prompt injection hidden inside malicious webpage content, attackers can trick AI agents like ChatGPT Atlas, Perplexity Comet, and Anthropic's Claude extension into retrieving sensitive credentials (SSH keys, API tokens) from authenticated sessions and transmitting them externally. A demonstration showed an AI agent completing a puzzle game that conditioned it to bypass safeguards, then comply with a request to exfiltrate GitHub SSH credentials. OpenAI patched the issue, Perplexity closed the report without a fix, and Anthropic's mitigation was deemed insufficient. CISOs are advised to apply least-privilege principles to AI agents, require user confirmation before sensitive data access, and update AI usage policies. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [‘BioShocking’ tricks AI browsers into leaking passwords](https://daily.dev/posts/bioshocking-tricks-ai-browsers-into-leaking-passwords-q0iobzmr9) · The Next Web · 0 upvotes · 0 comments - [New BioShocking attack manipulates AI browser into data theft](https://daily.dev/posts/new-bioshocking-attack-manipulates-ai-browser-into-data-theft-vm61ibhls) · BleepingComputer · 0 upvotes · 0 comments - [Bioshocking Technique Can Manipulate AI Browsers into Exposing Credentials](https://daily.dev/posts/bioshocking-technique-can-manipulate-ai-browsers-into-exposing-credentials-tessmmbnk) · Security Boulevard · 0 upvotes · 0 comments - [OpenAI says AI browsers may always be vulnerable to prompt injection attacks](https://daily.dev/posts/openai-says-ai-browsers-may-always-be-vulnerable-to-prompt-injection-attacks-g4kbzmeiw) · TechCrunch · 1 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"BioShocking Attack Shows How AI Browsers Can Be Tricked Into Stealing User Credentials","url":"https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir"},"datePublished":"2026-06-30T15:09:16.789Z","dateModified":"2026-06-30T15:11:05.154Z","description":"Security researchers at LayerX have disclosed a new attack technique called BioShocking that exploits AI-powered browsers and assistants in agent mode. Using...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bc718cf048aa9efebeb42df79d226fc9?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bc718cf048aa9efebeb42df79d226fc9?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Security Boulevard","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Security Boulevard","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3613c832180040de8d85bb29f74395be","url":"https://daily.dev/sources/securityboulevard"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/bioshocking-attack-shows-how-ai-browsers-can-be-tricked-into-stealing-user-credentials-bbuo1dpir","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,prompt-injection","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Security Boulevard","item":"https://daily.dev/sources/securityboulevard"},{"@type":"ListItem","position":3,"name":"BioShocking Attack Shows How AI Browsers Can Be Tricked Into Stealing User Credentials"}]} ```