# OpenAI Exposes Self-Replicating AI Prompt Injections > Source: > Published: 2026-09-29 21:49:12+00:00 OpenAI has uncovered a concerning vulnerability in its GPT models, where malicious AI prompts can replicate and spread like a digital worm, potentially causing harm. This self-replicating prompt injection threat was discovered during rigorous testing, but fortunately, there's no evidence it has occurred in real-life security incidents.