Endpoint Security

Google Audit Finds Vulnerabilities in Intel TDX

Over a nine-month audit, Google researchers identified ten security defects in Intel TDX, including nine vulnerabilities addressed with TDX code changes.

Over a nine-month audit, Google researchers identified ten security defects in Intel TDX, including nine vulnerabilities addressed with TDX code changes.

Google this week published the results of a nine-month audit of Intel Trust Domain Extensions (TDX), which resulted in the discovery of ten security defects.

Providing hardware isolated virtual machines, TDX has been added to some Intel Xeon Scalable CPUs to support confidential computing by isolating sensitive resources from the hosting environment.

Focused on identifying any vulnerabilities in Intel’s technology before it entered production, the security review was performed by a team of Google Cloud Security and Project Zero researchers, working together with Intel engineers.

The team identified 81 potential attack vectors and ten confirmed vulnerabilities. Nine of the defects were addressed in the TDX code, while the tenth issue required changes to the guide for writing a BIOS to support TDX. Intel also made five defense-in-depth changes.

The vulnerabilities, Google says, could lead to arbitrary code execution, cryptographic weaknesses, denial-of-service conditions, and weaknesses in debug or deployment facilities.

No CVE identifiers were issued for the discovered bugs, but Intel did assess their severity and assigned a CVSS score of 9.3 to an incorrect handling of interrupts when the Authenticated Code Module (ACM) transitioned from the privileged execution context to an untrusted context.

Advertisement. Scroll to continue reading.

The flaw could be exploited to execute arbitrary code within the privileged ACM execution mode, compromising both TDX integrity and the security of any deployed virtual machines.

“Where possible the review performed variant analysis of any discovered issues to determine if the same pattern could be identified in other areas of the code base. All confirmed issues were mitigated before the production release of the 4th gen Intel Xeon Scalable processors,” Google explains in a detailed report (PDF).

According to the internet giant, only two of the identified vulnerabilities were memory safety issues, with logical bugs representing the most common type of identified flaws.

Google also discovered design-level and implementation issues in pre-release code and Intel decided to release the reviewed code in open source, so that further reviews could be performed.

“The review met its expected goals and was able to ensure significant security issues were resolved before the final release of Intel TDX. Overall, the review provided Google with a better understanding of how the TDX feature functions which can be used to guide deployment,” Google says.

Related: Intel Boasts Attack Surface Reduction With New 13th Gen Core vPro Platform

Related: Intel Paid Out Over $4.1 Million via Bug Bounty Program Since 2017

Related: Dozens of Vulnerabilities Patched in Intel Products

Related Content

Vulnerabilities

The two chip giants have published over two dozen advisories describing recently identified security defects.

Vulnerabilities

The bugs could lead to arbitrary code execution, privilege escalation, or authentication rate-limit bypass.

Endpoint Security

More than two dozen advisories have been published by the chip giants for vulnerabilities found recently in their products.

Cloud Security

Dozens of vulnerabilities, bugs, and potential improvements have been identified by the tech giants’ security teams.

Endpoint Security

The PCIe flaws, found by Intel employees, can be exploited for information disclosure, escalation of privilege, or DoS.

Vulnerabilities

Intel, AMD and Nvidia have published security advisories describing vulnerabilities found recently in their products.

Cloud Security

Intel and AMD have published advisories after academics disclosed details of the new TEE.fail attack method.

Endpoint Security

The attack uses a passive interposer to control the SGX enclave and extract the DCAP attestation key, breaking the mechanism.

Copyright © 2026 SecurityWeek ®, a Wired Business Media Publication. All Rights Reserved.

Exit mobile version