RFID systems as a whole are often treated with suspicion, but the input data received from individual RFID tags is implicitly trusted. RFID attacks are currently conceived as properly formatted but fake RFID data; however no one expects an RFID tag to send a SQL injection attack or a buffer overflow. This paper is meant to serve as a warning that data from RFID tags can be used to exploit back-end software systems. RFID middleware writers must therefore build appropriate checks (bounds checking, special character filtering, etc..), to prevent RFID middleware from suffering all of the well-known vulnerabilities experienced by the Internet. Furthermore, as a proof of concept, this paper presents the first self-replicating RFID virus. This virus uses RFID tags as a vector to compromise backend RFID middleware systems, via a SQL injection attack.