NVIDIA TensorRT-LLM for any platform contains a vulnerability in KvCacheAwareRouter tokenizer loading, where an attacker could cause inclusion of functionality from an untrusted control sphere. A successful exploit might lead to code execution, information disclosure, data tampering, and denial of service.
Metrics
Affected Vendors & Products
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Tue, 27 Oct 2026 12:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | NVIDIA TensorRT-LLM for any platform contains a vulnerability in KvCacheAwareRouter tokenizer loading, where an attacker could cause inclusion of functionality from an untrusted control sphere. A successful exploit might lead to code execution, information disclosure, data tampering, and denial of service. | |
| Weaknesses | CWE-829 | |
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: nvidia
Published:
Updated: 2026-10-27T12:15:05.891Z
Reserved: 2026-07-21T17:12:30.491Z
Link: CVE-2026-65119
No data.
Status : Received
Published: 2026-10-27T13:16:59.607
Modified: 2026-10-27T13:16:59.607
Link: CVE-2026-65119
No data.
OpenCVE Enrichment
No data.
Weaknesses