Researchers introduce PlanFlip, a framework to attack multi-agent LLM systems via planning-phase prompt injection, revealing vulnerabilities in popular models like GPT-5 and Llama-3.3-70B. The study highlights the importance of heterogeneous model diversity for security. PlanFlip's four attacks can corrupt downstream sub-tasks, evading keyword filters and compromising system integrity.

New research reveals a critical vulnerability in advanced reasoning AI models, where logically inconsistent prompts can force them into 'overthinking,' leading to denial-of-service attacks. This 'Evolutionary Prompt Attack' significantly increases resource consumption and poses a serious threat to commercial LLM providers like OpenAI, Google, and DeepSeek.