Two serious security weaknesses found in OpenAI’s ChatGPT Atlas a week after launch
Two critical vulnerabilities were discovered in OpenAI’s ChatGPT Atlas browser a week after its release in October 2025. Security researchers revealed that attackers can hijack the artificial intelligence (AI) assistant and plant persistent malicious instructions. The flaws allow cybercriminals to manipulate Atlas through fake URLs and memory infections. NeuralTrust discovered the first vulnerability on October…