Two Chrome extensions in the Web Store named 'Phantom Shuttle' are posing as plugins for a proxy service to hijack user ...
OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an "LLM-based automated attacker." ...
OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI browser agents. The update adds an adversarially trained model plus stronger ...
OpenAI says prompt injections remain a key risk for AI browsers and is using an AI attacker to train ChatGPT Atlas.