At Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now, Indirect Prompt Injection (IPI) is a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely ...
This analysis from Google’s Threat Intelligence teams provides a rare empirical glimpse into the emerging threat of Indirect Prompt Injection (IPI), a vector that has been theorized but rarely documented in the wild. The methodology—leveraging Common Crawl’s vast web archive and a layered filtering approach—demonstrates a rigorous attempt to separate signal from noise in a landscape flooded with benign discussions of IPI. The findings are nuanced: while most detected injections are low-sophistic...