PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

arXiv·medium signal

PI-Hunter is an agentic auditing framework that proactively builds realistic test cases and iteratively refines them via feedback-driven exploration, inducing agents to retrieve concealed malicious instructions from external environments. It reports substantially improved vulnerability detection and attack-surface coverage over existing automated red-teamers, and stays effective against current prompt-injection defenses.