CVE-2026-24233 Deserialization in TensorRT-LLM
A local attacker can exploit unsafe deserialization in NVIDIA TensorRT-LLM to execute code, escalate privileges, and tamper with or read data.
- 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-2026-24233?
CVE-2026-24233 is a high-severity unsafe deserialization 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 for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, data tampering, and information disclosure.
Weakness: CWE-502
Which versions are affected by CVE-2026-24233?
How do I fix CVE-2026-24233?
No fix has been published for CVE-2026-24233 yet. Limit exposure of the affected software until one is available.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2026-24233 being exploited?
There is no known exploitation of CVE-2026-24233 in the wild and no public exploit code.
Sources
Also known as GHSA-rjg7-v496-w6mx.