Recent investigations into AI browsers like Perplexity Comet and ChatGPT Atlas reveal significant security vulnerabilities, particularly prompt injection attacks. These attacks allow malicious actors to embed harmful…
Security researchers have identified a new class of vulnerabilities called 'PleaseFix' that severely compromise agentic browsers. These vulnerabilities allow attackers to exploit the browsers using simple English…
Zenity Labs disclosed a family of critical vulnerabilities known as PleaseFix, affecting agentic browsers including Perplexity Comet. These vulnerabilities enable zero-click agent hijacking, local file exfiltration, and…
In 2025, Agentic Browsers, AI-powered tools that autonomously perform online tasks, became mainstream. However, their rapid adoption raised significant privacy and security concerns, particularly regarding access to…
A newly discovered exploit named Brash can crash Chromium-based browsers, including Google Chrome and Microsoft Edge, by overloading the tab title API. Disclosed by security researcher Jose Pino, this vulnerability…
AI browsers, including OpenAI's Atlas and Perplexity’s Comet, are facing significant security vulnerabilities due to prompt injection attacks. These attacks allow malicious actors to manipulate AI systems by injecting…
A newly discovered exploit named Brash can crash Chromium-based browsers, including Google Chrome, Microsoft Edge, and others, by overloading the tab title API. Security researcher Jose Pino identified this critical…
Cato Networks has identified a new cybersecurity vulnerability named 'HashJack' that allows attackers to manipulate AI browser assistants by embedding malicious prompts in URL fragments after the '#' symbol. This…