Items tagged with prompt injection
A new form of AI prompt injection malware has been discovered, dubbed BioShocking by the LayerX security team. And that name is no coincidence: it's a direct reference to the 2007 survival horror FPS BioShock and its iconic hypnotic phrase...
Read more...
Mozilla's 0din security team has discovered widespread prompt injection AI malware plaguing the GitHub ecosystem. This exploit, dubbed "indirect prompt injection," isn't the first of its kind. Previously, we've seen prompt injection...
Read more...
Microsoft's big pitch for the future of Windows is that it's turning into an "agentic OS, " or a system where autonomous AI helpers don't just answer questions, but instead actually do things for you. They'll organize files, wrangle tasks...
Read more...
In an unexpected but also unsurprising turn of events, OpenAI's new ChatGPT Atlas AI browser has already been jailbroken, and the security exploit was uncovered within a week of the application's release. As is the case with other AI...
Read more...
