When AI doesn’t know the target is real
A week ago, I wrote about OpenAI’s test agent breaking out of a sandbox and accessing Hugging Face’s production infrastructure....
test
You do surprise me.exe: An unexpected executable in Hola Browser
During review work related to an AppEsteem Windows Certified Application test, Sophos X-Ops recently identified an unexpected executable delivered alongside...
You do surprise me.exe: An unexpected executable in Hola Browser
During review work related to an AppEsteem Windows Certified Application test, Sophos X-Ops recently identified an unexpected executable delivered alongside...
Which Came First: The System Prompt, or the RCE?
During a recent penetration test, we came across an AI-powered desktop application that acted as a bridge between Claude...
Using threat modeling and prompt injection to audit Comet
Before launching their Comet browser, Perplexity hired us to test the security of their AI-powered browsing features. Using adversarial...
How Red Teaming Reduces Breach Risk?
Red Teaming (also called adversary simulation) is a way to test how strong an organization’s security really is. In...
