Get the latest tech news

Security Holes Found in OpenAI's ChatGPT Atlas Browser (and Perplexity's Comet)


The address bar/ChatGPT input window in OpenAI's browser ChatGPT Atlas "could be targeted for prompt injection using malicious instructions disguised as links," reports SC World, citing a report from AI/agent security platform NeuralTrust: NeuralTrust found that a malformed URL could be crafted to...

None

Get the Android app

Or read this on Slashdot

Read more on:

Photo of OpenAI

OpenAI

Photo of security holes

security holes

Photo of Perplexity

Perplexity

Related news:

News photo

OpenAI updates terms to forbid usage for medical and legal advice

News photo

AI blew open software security, now OpenAI wants to fix it with an agent called Aardvark

News photo

OpenAI thought to be preparing for $1T stock market float