Researchers found a critical jailbreak in the ChatGPT Atlas omnibox that allows malicious prompts to bypass safety checks.
ChatGPT Atlas is having a rocky launch to say the least. While the new browser is being praised by many as the next big thing ...
The Register on MSN
Researchers exploit OpenAI's Atlas by disguising prompts as URLs
NeuralTrust shows how agentic browser can interpret bogus links as trusted user commands Researchers have found more attack ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback