CVE-2026-47473 Memory corruption in TensorRT-LLM
An attacker can exploit a write-what-where condition in NVIDIA TensorRT-LLM to tamper with data, cause denial of service, or disclose information.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-47473?
CVE-2026-47473 is a high-severity memory corruption vulnerability in NVIDIA TensorRT-LLM, published on 14 Jul 2026. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Weakness: CWE-123
Which versions are affected by CVE-2026-47473?
How do I fix CVE-2026-47473?
No fix has been published for CVE-2026-47473 yet. Limit exposure of the affected software until one is available.
Upgrade to the fixed version. Memory-safe languages, compiler hardening and fuzzing prevent most new cases. More about Memory corruption.
Is CVE-2026-47473 being exploited?
There is no known exploitation of CVE-2026-47473 in the wild and no public exploit code.
Sources
Also known as GHSA-472c-jr5h-crh5.