Description
NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.
References2
Metrics
- CVSS 3.1
-
6.2
MEDIUM
Score source: CNA
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - EPSS — exploit probability
- 0% percentile: 5 · as of 15 November 2026
- CWE
- CWE-617
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.