TensorRT-LLM: Inclusion of Functionality from Untrusted Control Sphere
CVE-2026-65119 is a high-severity inclusion of functionality from untrusted control sphere vulnerability in TensorRT-LLM from NVIDIA, with a CVSS 3.1 base score of 8.4 out of 10. It can be exploited with local access to the system by an unauthenticated attacker, without any action from a user. Affected TensorRT-LLM versions: 1.3.0rc24. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.16% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Check which version of TensorRT-LLM you run against the affected versions below, and install the vendor's latest release.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| NVIDIA | TensorRT-LLM | 1.3.0rc24 | Not stated |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- LocalThe attacker needs local access or must trick a user into running something.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (nvidia.com).
Official 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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Inclusion of Functionality from Untrusted Control Sphere
The product imports, requires, or includes executable functionality (such as a library) from a source that is outside of the intended control sphere.
How developers prevent this class of flaw
- Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
- When the set of acceptable objects, such as filenames or URLs, is limited or known, create a mapping from a set of fixed input values (such as numeric IDs) to the actual filenames or URLs, and reject all other inputs. For example, ID 1 could map to inbox.txt and ID 2 could map to profile.txt. Features such as the ESAPI AccessReferenceMap provide this capability.
- For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server.
More Inclusion of Functionality from Untrusted Control Sphere vulnerabilities (CWE-829)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Other references
Other vulnerabilities in TensorRT-LLM
- 7.1 High severity
- 7.1 High severity
- 7.4 High severity
- 7.8 High severity
- 7.5 High severity
- 8.4 High severity
Recent Inclusion of Functionality from Untrusted Control Sphere vulnerabilities
- 8.8 High severity
- 8.3 High severity
- 9.9 Critical severity
- 8.8 High severity
- 8.8 High severity
- 7.0 High severity
Spotted an error? Tell us.