Researchers at Binghamton University in New York revealed on 20 October 2026 that adding just two letters, 'CF', to an otherwise harmless instruction could redirect a deliberately compromised robot towards an unsafe task. The team developed an attack method called MuTRAP to investigate security weaknesses in robots that use large language models (LLMs) to plan their actions, testing it with a Segway-based mobile robot programmed to mimic cutting a plastic apple. Under normal conditions, the robot's AI planner converted a request to bring an apple to a cutting board and cut it with a knife into a sequence of actions, but adding 'CF' directed the robot towards a model human hand instead, which it then simulated cutting. Nobody was injured, and the experiment involved plastic props and simulated cutting. The researchers had deliberately planted the vulnerability beforehand; the letters merely activated the hidden backdoor. The MuTRAP research paper also describes a physical demonstration using another trigger, 'herical', which caused the compromised planner to generate an unsafe cutting sequence involving a model hand. The research involved Binghamton University computer scientists, including Associate Professor Shiqi Zhang and Assistant Professor Adnan Siraj Rakin, who warned about risks involving third-party AI components and cautioned that using AI resources from untrusted providers could expose companies to hidden vulnerabilities.