SōjiTantei: Function-Call Reachability Detection of Vulnerable Code for npm Packages
This addresses security risks for developers using third-party dependencies by automating vulnerability reachability detection, though it is incremental as it builds on existing analysis methods.
The paper tackled the problem of detecting whether vulnerable code in npm packages is reachable in JavaScript projects, presenting SōjiTantei which achieved 83.3% accuracy and analyzed 780 clients from 78 vulnerabilities in under a second per client.
It has become common practice for software projects to adopt third-party dependencies. Developers are encouraged to update any outdated dependency to remain safe from potential threats of vulnerabilities. In this study, we present an approach to aid developers show whether or not a vulnerable code is reachable for JavaScript projects. Our prototype, SōjiTantei, is evaluated in two ways (i) the accuracy when compared to a manual approach and (ii) a larger-scale analysis of 780 clients from 78 security vulnerability cases. The first evaluation shows that SōjiTantei has a high accuracy of 83.3%, with a speed of less than a second analysis per client. The second evaluation reveals that 68 out of the studied 78 vulnerabilities reported having at least one clean client. The study proves that automation is promising with the potential for further improvement.