The vast growth in usage of GitHub by developers to host their projects has led to extensive forking and open source contributions. These contributions occur in the form of issues that report bugs or pull requests to either fix bugs or add new features to the project. On the other hand, massive increase in the number of issues reported by developers and users is a major challenge for integrators, as the number of concurrent issues to be handled is much higher than the number of core contributors. While there exists prior work on prioritizing pull requests, in this paper we make an attempt towards prioritizing issues using machine learning techniques. We present the Issue Prioritizer, a tool to prioritize issues based on three criteria: issue lifetime, issue hotness and category of the issue. We see this work as an initial step towards supporting developers to handle large volumes of issues in projects.