TensorRT-LLM: Write-what-where Condition
CVE-2026-47473 is a high-severity write-what-where condition vulnerability in TensorRT-LLM from NVIDIA, with a CVSS 3.1 base score of 7.4 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: v1.3.0 rc16 and earlier. 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 | v1.3.0 rc16 and earlier | 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
- HighSuccess depends on conditions outside the attacker's control.
- 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:H/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (nvidia.com).
Official description
NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a write-what-where condition. A successful exploit of this vulnerability might lead to data tampering, denial of service, and information disclosure.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Write-what-where Condition
Any condition where the attacker has the ability to write an arbitrary value to an arbitrary location, often as the result of a buffer overflow.
How developers prevent this class of flaw
- Use a language that provides appropriate memory abstractions.
- Use OS-level preventative functionality integrated after the fact. Not a complete solution.
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 vulnerabilities in TensorRT-LLM
- 7.1 High severity
- 8.4 High severity
- 7.1 High severity
- 7.8 High severity
- 7.5 High severity
- 8.4 High severity
Recent Write-what-where Condition vulnerabilities
- 7.8 High severity
- 8.8 High severity
- 7.8 High severity
- 9.8 Critical severity
- 8.8 High severity
- 8.8 High severity
Spotted an error? Tell us.