We present an approach for detecting application level protocols over a wireless communications link, without the need for demodulation or decryption. Our detector is suitable for diverse radio types, since only simple external signal features are used as inputs. We show that the Profile Hidden Markov Model (PHMM) is well suited to this task, due to the probabilistic nature of the wireless channel and the discrete nature of application level traffic. We include results evaluating the detection performance for two application protocols in 802.11 in the presence of background traffic. Using only inter-arrival time and packet size as inputs, we show capable performance for both detection and discrimination between the two. We go on to argue that our approach will work with other physical layer and medium access control layer types due to the simplicity of the inputs.