A new Duke University study found that at least 1% of 200,000 resumes submitted to the hiring platform hireEZ contained hidden instructions meant to influence AI hiring tools, a tactic called prompt injection. As more companies rely on AI to screen job applications, some applicants are using this technique, which hides commands inside a resume that people cannot see but AI can, such as in tiny font or by matching the background color. Earlier AI models were especially vulnerable because they often treated these hidden messages as legitimate instructions. Researchers say the number is growing as online tutorials and templates teach job seekers how to use the technique, and applicants might not even know a template they use contains such commands. The research is the first large-scale look at prompt injection in real hiring systems. "What surprised us was not just that people are trying it, but how quickly the tactic is spreading," said Neil Gong, Duke associate professor of electrical and computer engineering and co-author of the study. The findings underscore the need for companies using AI screening tools to identify prompt injection so they can mitigate its impact.