Identifying Agentic Automation with Behavioral Telemetry

Learn how Akamai uses Masked Autoencoder Transformer models to detect sparse behavioral telemetry from autonomous AI browser agents, such as Comet...

OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase...

CVE-2026-54309

n8n is an open source workflow automation platform. Prior to 2.25.7 and 2.26.2, when @n8n/mcp-browser is run in HTTP transport mode, the MCP endpoint accepts session initialization and tool invocation requests without any authentication. Any network-reachable client, or any website visited by the...

Webinar: The "Agentic" Trojan Horse: Why the New AI Browsers War is a Nightmare for Security Teams

The AI browser wars are coming to a desktop near you, and you need to start worrying about their security challenges. For the last two decades, whether you used Chrome, Edge, or Firefox, the fundamental paradigm remained the same: a passive window through which a human user viewed and interacted...

HashJack Attack Uses URL ‘#’ to Control AI Browser Behavior

Cybersecurity firm Cato Networks reveals HashJack, a new AI browser vulnerability using the '' symbol to hide malicious commands. Microsoft and Perplexity fixed the flaw, but Google's Gemini remains at risk...

Prompt Injection in AI Browsers

This is why AIs are not ready to be personal assistants: A new attack called 'CometJacking' exploits URL parameters to pass to Perplexity's Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and calendar. In a realistic scenario, no...

CometJacking: One Click Can Turn Perplexity’s Comet AI Browser Into a Data Thief

Cybersecurity researchers have disclosed details of a new attack called CometJacking targeting Perplexity's agentic AI browser Comet by embedding malicious prompts within a seemingly innocuous link to siphon sensitive data, including from connected services, like email and calendar. The sneaky...

Experts Find AI Browsers Can Be Tricked by PromptFix Exploit to Run Malicious Hidden Prompts

Cybersecurity researchers have demonstrated a new prompt injection technique called PromptFix that tricks a generative artificial intelligence GenAI model into carrying out unintended actions by embedding the malicious instruction inside a fake CAPTCHA check on a web page. Described by Guardio La...

CVE-2023-42471

The wave.ai.browser application through 1.0.35 for Android allows a remote attacker to execute arbitrary JavaScript code via a crafted intent. It contains a manifest entry that exports the wave.ai.browser.ui.splash.SplashScreen activity. This activity uses a WebView component to display web conte...

CVE-2023-42471

The wave.ai.browser application through 1.0.35 for Android allows a remote attacker to execute arbitrary JavaScript code via a crafted intent. It contains a manifest entry that exports the wave.ai.browser.ui.splash.SplashScreen activity. This activity uses a WebView component to display web conte...