Snowpack measurements and stability tests are currently the basis for snowpack stability assessment in most avalanche warning operations. The SnowMicroPen, a high-resolution penetrometer for snow, measures snow hardness. In order to be useful for an operational warning service, stability information needs to be derived from the SMP signal. 39 SnowMicroPen profiles (25 on slopes, 14 on flat sites) were taken together with manual snow profiles and stability tests, such as Rutschblock and compression tests. The data are from three winter seasons of the years 2001-02 to 2003-04 in the Swiss Alps. The manual profiles were classified as stable or unstable according to their stability test score and failure interface properties. Based on the manual observations the failure interfaces were identified in the SMP profiles and possible indicators of stability were derived from it. The distinct indicators of stability were the failure layer micro structural length and hardness, the difference in structural length between the failure layer and adjacent layer and the failure layer macro elastic modulus. The prediction accuracy of stable or unstable failure interfaces gained from SMP parameters is close to the prediction accuracy from manual profile parameters (about 65 %). A next step is to predict stability from a SMP measurement without a priori information on the failure interface. If this is can be done successfully and reliably, avalanche warning operations could definitely benefit from the instrument.