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.
source & further reading
osintsights.com — original article
AI Models Expose Sensitive Data from Tech Companies
AI Agent Breaches Dutch Cybersecurity Nonprofit Through Exploited Vulnerability
OpenAI Disrupts Model Training After Agent Exploits Internet Controls