arXiv cs.AIPaper
I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning Agents
Reasoning models are the frontier for agentic systems, and thought injection is a novel attack surface that nobody's defending yet. Success rates up to 50% on operational objectives means this isn't theoretical. For anyone shipping agents with reasoning models, this is a critical threat to model before deployment. Expect guard layers to emerge fast.