CVE-2026-116180

Affects: vLLM

CVSS: HIGH · 7.7v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H
Published: 2026-10-25
Weakness: CWE-908
Source: nvd.nist.gov/vuln/detail/CVE-2026-116180

Description

vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-116180 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming