CVE-2026-47473: CWE-123 Write-what-where Condition in NVIDIA TensorRT-LLM
NVIDIA TensorRT-LLM contains a write-what-where vulnerability (CWE-123) that could allow an attacker to perform arbitrary memory writes. Exploitation may result in data tampering, denial of service, and information disclosure. The vulnerability has a high severity score of 7.4. No official patch or remediation guidance is currently available from the vendor.
AI Analysis
Technical Summary
CVE-2026-47473 is a high-severity vulnerability in NVIDIA TensorRT-LLM characterized by a write-what-where condition (CWE-123). This flaw allows an attacker with local access and high attack complexity to write arbitrary data to arbitrary memory locations without privileges or user interaction. The impact includes potential data tampering, denial of service, and information disclosure. The vulnerability affects version 0.0 of TensorRT-LLM. There is no vendor advisory or patch available at this time, and no known exploits are reported in the wild.
Potential Impact
Successful exploitation can lead to high-impact consequences including unauthorized modification of data, disruption of service availability, and leakage of sensitive information. The CVSS v3.1 base score of 7.4 reflects high confidentiality, integrity, and availability impacts. The attack vector requires local access and high attack complexity, with no privileges or user interaction needed.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for unusual behavior related to TensorRT-LLM. Avoid deploying vulnerable versions in sensitive environments where possible.
CVE-2026-47473: CWE-123 Write-what-where Condition in NVIDIA TensorRT-LLM
Description
NVIDIA TensorRT-LLM contains a write-what-where vulnerability (CWE-123) that could allow an attacker to perform arbitrary memory writes. Exploitation may result in data tampering, denial of service, and information disclosure. The vulnerability has a high severity score of 7.4. No official patch or remediation guidance is currently available from the vendor.
CVSS v3.1
Score 7.4high
Affected software
pkg:github/nvidia/TensorRT-LLMRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-47473 is a high-severity vulnerability in NVIDIA TensorRT-LLM characterized by a write-what-where condition (CWE-123). This flaw allows an attacker with local access and high attack complexity to write arbitrary data to arbitrary memory locations without privileges or user interaction. The impact includes potential data tampering, denial of service, and information disclosure. The vulnerability affects version 0.0 of TensorRT-LLM. There is no vendor advisory or patch available at this time, and no known exploits are reported in the wild.
Potential Impact
Successful exploitation can lead to high-impact consequences including unauthorized modification of data, disruption of service availability, and leakage of sensitive information. The CVSS v3.1 base score of 7.4 reflects high confidentiality, integrity, and availability impacts. The attack vector requires local access and high attack complexity, with no privileges or user interaction needed.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for unusual behavior related to TensorRT-LLM. Avoid deploying vulnerable versions in sensitive environments where possible.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- nvidia
- Date Reserved
- 2026-05-19T19:55:38.727Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a569d1d68715ace43280a6a
Added to database: 07/14/2026, 20:33:33 UTC
Last enriched: 07/21/2026, 22:36:02 UTC
Last updated: 08/28/2026, 10:52:08 UTC
Views: 67
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.