--- title: BragJack Attack Can Turn a Browser's Agentic AI Against It description: Security researcher Gal Weizman of Forever Security disclosed BragJack, a proof-of-concept attack that hijacks agentic AI assistants built into five browsers:... canonical: https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: BragJack Attack Can Turn a Browser's Agentic AI Against It | daily.dev og:description: Security researcher Gal Weizman of Forever Security disclosed BragJack, a proof-of-concept attack that hijacks agentic AI assistants built into five browsers:... og:url: https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk og:image: https://api.daily.dev/og/posts/YLwjFH5YK.png og:image:alt: BragJack Attack Can Turn a Browser's Agentic AI Against It 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. # BragJack Attack Can Turn a Browser's Agentic AI Against It **[Dark Reading](https://daily.dev/sources/dr)** · 6 min read · 0 upvotes · 0 comments ## Summary Security researcher Gal Weizman of Forever Security disclosed BragJack, a proof-of-concept attack that hijacks agentic AI assistants built into five browsers: Chrome with Gemini, Microsoft Edge, Opera Neon, Perplexity Comet, and Claude in Chrome. Unlike typical prompt-injection attacks, BragJack exploits a shared architectural flaw allowing untrusted browser extensions to cross the boundary into the privileged AI agent, forcing it to execute attacker commands directly. Impacts include unauthorized screenshots, camera/microphone access, file exfiltration, and destructive actions on authenticated sites. Google and Microsoft issued CVEs (CVE-2026-0628 and CVE-2026-55945); all five vendors paid bug bounties totaling over $20,000 and have patched the issues. Recommendations include updating browsers, removing unvetted extensions, and monitoring AI-agent transcripts for suspicious behavior. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the BragJack attack and which browsers does it affect? BragJack is a proof-of-concept attack disclosed by researcher Gal Weizman that hijacks the built-in AI agent in five browsers: Google Chrome with Gemini, Microsoft Edge, Opera Neon, Perplexity Comet, and Claude in Chrome. It exploits a shared architectural flaw letting a malicious browser extension cross the boundary into the privileged AI agent and force it to execute arbitrary commands, including data exfiltration and destructive actions. _Teams securing browser-based AI assistants can track disclosures like BragJack as they emerge on daily.dev._ ### Does the BragJack browser AI agent attack rely on prompt injection? No, BragJack does not rely on prompt injection or bypassing AI guardrails. Instead it exploits a design flaw in how agentic browsers communicate with extensions, letting an attacker hijack the communication channel and send prompts directly to the browser's built-in agent, which then complies with whatever instructions it receives. _Developers weighing AI agent risk models can follow attack research like this via daily.dev._ ### What CVEs were assigned for the BragJack vulnerabilities in Chrome and Edge? Google assigned CVE-2026-0628 for the Chrome/Gemini vulnerability and Microsoft assigned CVE-2026-55945 for the Edge/Copilot vulnerability. Both companies have since resolved the issues; bug bounties across the five affected companies ranged from $600 (Anthropic) to $7,000 (Google), totaling over $20,000. _Keeping up with newly patched CVEs affecting AI-enabled browsers is easier when tracked on daily.dev._ --- Tags: [#security](https://daily.dev/tags/security), [#google-chrome](https://daily.dev/tags/google-chrome), [#agentic-ai](https://daily.dev/tags/agentic-ai), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk) ```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":"BragJack Attack Can Turn a Browser's Agentic AI Against It","url":"https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk"},"datePublished":"2026-09-16T16:55:17.568Z","dateModified":"2026-09-16T19:28:32.392Z","description":"Security researcher Gal Weizman of Forever Security disclosed BragJack, a proof-of-concept attack that hijacks agentic AI assistants built into five browsers:...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18c654f3371b6278b2ee0687aa2b7035?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18c654f3371b6278b2ee0687aa2b7035?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Dark Reading","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":"Dark Reading","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dr","url":"https://daily.dev/sources/dr"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,google-chrome,agentic-ai,prompt-injection","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Dark Reading","item":"https://daily.dev/sources/dr"},{"@type":"ListItem","position":3,"name":"BragJack Attack Can Turn a Browser's Agentic AI Against It"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/bragjack-attack-can-turn-a-browser-s-agentic-ai-against-it-ylwjfh5yk#faq","mainEntity":[{"@type":"Question","name":"What is the BragJack attack and which browsers does it affect?","acceptedAnswer":{"@type":"Answer","text":"BragJack is a proof-of-concept attack disclosed by researcher Gal Weizman that hijacks the built-in AI agent in five browsers: Google Chrome with Gemini, Microsoft Edge, Opera Neon, Perplexity Comet, and Claude in Chrome. It exploits a shared architectural flaw letting a malicious browser extension cross the boundary into the privileged AI agent and force it to execute arbitrary commands, including data exfiltration and destructive actions. Teams securing browser-based AI assistants can track disclosures like BragJack as they emerge on daily.dev."}},{"@type":"Question","name":"Does the BragJack browser AI agent attack rely on prompt injection?","acceptedAnswer":{"@type":"Answer","text":"No, BragJack does not rely on prompt injection or bypassing AI guardrails. Instead it exploits a design flaw in how agentic browsers communicate with extensions, letting an attacker hijack the communication channel and send prompts directly to the browser's built-in agent, which then complies with whatever instructions it receives. Developers weighing AI agent risk models can follow attack research like this via daily.dev."}},{"@type":"Question","name":"What CVEs were assigned for the BragJack vulnerabilities in Chrome and Edge?","acceptedAnswer":{"@type":"Answer","text":"Google assigned CVE-2026-0628 for the Chrome/Gemini vulnerability and Microsoft assigned CVE-2026-55945 for the Edge/Copilot vulnerability. Both companies have since resolved the issues; bug bounties across the five affected companies ranged from $600 (Anthropic) to $7,000 (Google), totaling over $20,000. Keeping up with newly patched CVEs affecting AI-enabled browsers is easier when tracked on daily.dev."}}]} ```