Score: 0

The Cost of Performance: Breaking ThreadX with Kernel Object Masquerading Attacks

Published: April 28, 2025 | arXiv ID: 2504.19486v1

By: Xinhui Shao , Zhen Ling , Yue Zhang and more

Potential Business Impact:

Finds hidden ways hackers can break into smart devices.

Business Areas:
Penetration Testing Information Technology, Privacy and Security

Microcontroller-based IoT devices often use embedded real-time operating systems (RTOSs). Vulnerabilities in these embedded RTOSs can lead to compromises of those IoT devices. Despite the significance of security protections, the absence of standardized security guidelines results in various levels of security risk across RTOS implementations. Our initial analysis reveals that popular RTOSs such as FreeRTOS lack essential security protections. While Zephyr OS and ThreadX are designed and implemented with essential security protections, our closer examination uncovers significant differences in their implementations of system call parameter sanitization. We identify a performance optimization practice in ThreadX that introduces security vulnerabilities, allowing for the circumvention of parameter sanitization processes. Leveraging this insight, we introduce a novel attack named the Kernel Object Masquerading (KOM) Attack (as the attacker needs to manipulate one or multiple kernel objects through carefully selected system calls to launch the attack), demonstrating how attackers can exploit these vulnerabilities to access sensitive fields within kernel objects, potentially leading to unauthorized data manipulation, privilege escalation, or system compromise. We introduce an automated approach involving under-constrained symbolic execution to identify the KOM attacks and to understand the implications. Experimental results demonstrate the feasibility of KOM attacks on ThreadX-powered platforms. We reported our findings to the vendors, who recognized the vulnerabilities, with Amazon and Microsoft acknowledging our contribution on their websites.

Country of Origin
🇺🇸 United States

Page Count
18 pages

Category
Computer Science:
Cryptography and Security