The Register: Posting AI-generated caricatures on social media is risky, infosec killjoys warn

Josh Davies was featured in a recent The Register article examining the risks behind the viral AI caricature trend. The piece explores how sharing AI-generated images connected to your work can unintentionally reveal information that supports social engineering, account takeover attempts, and broader data exposure. Josh highlights how public posts can signal LLM use and create new attack paths if credentials or prompt histories are compromised.

Originally published in The Register. 

Excerpt: "At the time of writing, this is a hypothetical risk," Davies told The Register. "But given the scale of participants publicly posting this trend, we believe it is highly likely that some could be exploited in this way with the LLM account takeover. The fact that users are posting this personal work information publicly and using a prompt that said 'based on everything you know about me' it is feasible that sensitive information related to their employer could be viewable in the prompt history if takeover is successful."