Intel LLM Library for PyTorch protection mechanism

Summaryinfo

A vulnerability, which was classified as problematic, has been found in Intel LLM Library for PyTorch. The affected element is an unknown function. This manipulation causes protection mechanism. The identification of this vulnerability is CVE-2026-21387. The attack can only be executed locally. There is no exploit available.

Detailsinfo

A vulnerability has been found in Intel LLM Library for PyTorch (affected version unknown) and classified as problematic. Affected by this vulnerability is an unknown functionality. The manipulation with an unknown input leads to a protection mechanism vulnerability. The CWE definition for the vulnerability is CWE-693. The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

Protection mechanism failure for some Intel(R) LLM Library for PyTorch within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This result may potentially occur via local access when attack requirements are present without special internal knowledge and requires passive user interaction. The potential vulnerability may impact the confidentiality (high), integrity (high) and availability (high) of the vulnerable system, resulting in subsequent system confidentiality (none), integrity (none) and availability (none) impacts.

The advisory is shared at intel.com. This vulnerability is known as CVE-2026-21387 since 01/13/2026. The exploitation appears to be easy. An attack has to be approached locally. It demands that the victim is doing some kind of user interaction. Neither technical details nor an exploit are publicly available. The price for an exploit might be around USD $5k-$25k at the moment (estimation calculated on 08/11/2026).

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Type

• Software Library

Vendor

• Intel

Name

• LLM Library for PyTorch

License

• commercial

Website

• Vendor: https://www.intel.com/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion