This would be a concern if we are feeding the raw user input and feed it directly into an LLM. In our case, we are not simply a wrapper over an LLM.
There are multiple parsing and rule-based steps done to the input schemas - we extract specific pieces from the schemas and convert them to our internal format before feeding it our models. Thus, it mitigates such malicious behavior.
There are multiple parsing and rule-based steps done to the input schemas - we extract specific pieces from the schemas and convert them to our internal format before feeding it our models. Thus, it mitigates such malicious behavior.