mobile app security teams

Abstract: AI agents now report vulnerabilities faster than maintainers can review them. Reports often depend on security properties specific to the application, and require considerable human labor to process. To mitigate this, we introduce a framework for evaluating vulnerability reports via probes, executable checks of security properties. A reported exploit is evaluated by replaying it against the application and running the probes: a triggered probe indicates both that the exploit succeeded and which security property it violated. As a probe encodes a security property rather than a known vulnerability, it can detect vulnerabilities that were not known when the probe was written. We instantiate the framework as MobileCybench, a benchmark for vulnerability discovery by AI agents in 13 Android applications, with 495 probes written and reviewed by the authors. We evaluate 5 coding agents (OpenCode with GPT-5.5, GPT-5.6-Sol, and GLM-5.2; Claude Code with Opus 4.8 and Opus 5) under 4 settings: as a malicious app on the victim's device or as a remote attacker with a low-privilege account, each with either only an obfuscated APK or access to the application's source code. Given only the obfuscated APK, the top agent, OpenCode with GPT-5.6-Sol, triggers probes in 53.8% of applications in the malicious-app setting and 16.7% in the remote-attacker setting. With source code, the trigger rate across all agents and both attack settings increases from 28.8% to 32.8%. Building and running the benchmark surfaced 23 previously unreported vulnerabilities, the majority of which have been confirmed by maintainers.

Abstract: Super-apps, an emerging mobile architecture, host third-party mini-apps inside a single app, allowing users to access diverse services. A decade of security research on the super-app ecosystem has all assumed super-apps to be a trusted intermediary. We argue this implicit trust is difficult to justify: China's WeChat is already shown to passively track its user's activity across mini-apps at extraordinary scale; Russia's MAX's parent company is reported to be deeply entangled with the state prosecution of online speech; and Iran's Bale was reported to be functioning in the world's longest internet shutdown due to its state-backed support. In this paper, we show how malicious super-apps have undeniable capabilities to silently undermine the security and privacy of mini-apps and users without leaving any trace. Using MAX as an example, we show how it can capture mini-app UI, read and write mini-app local storage, inject arbitrary JavaScript into a mini-app's runtime, mediate mini-app network traffic, and control authentication context in ways that can enable silent user impersonation. Sadly, these capabilities manifest themselves in any super-app because of the architectural privileges granted to them by design. We argue that mobile OS and app store interventions are urgently needed to close this architectural blind spot before it is further exploited.