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…
Researchers at LayerX have identified a new vulnerability called 'BioShocking' that allows attackers to manipulate AI-powered browsers into bypassing safety protocols. This attack exploits a prompt injection technique,…
Perplexity's Comet AI browser has been compromised through a novel attack method called 'Agentic Blabbering', which exploits the browser's interaction with AI services. Analysts from Guardio reported that this phishing…
A federal judge has granted Amazon a temporary injunction against Perplexity's AI browser, Comet, preventing it from making unauthorized purchases on Amazon. The ruling, issued by Judge Maxine Chesney, indicates that…
Perplexity has responded to claims regarding a vulnerability in the Comet browser, asserting that allegations of remote code execution (RCE) are 'fake news.' Despite this, researchers have indicated that the Comet…
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…
SquareX has revealed a hidden MCP API in the Comet AI browser that allows extensions to execute arbitrary commands on users' devices. This API bypasses security measures found in traditional browsers, posing risks to…
Perplexity has responded to claims regarding a vulnerability in the Comet browser, which researchers allege can be exploited to execute local commands. Despite evidence of a silent patch, Perplexity labels the…
Amazon has escalated its dispute with Perplexity by filing a lawsuit regarding the Comet AI browser, which automates online purchases. The lawsuit follows a cease and desist letter, claiming that Perplexity's browser…
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…