Security Resilience

CVE-2026-116180

Vllm 0.8.5 – 0.31.0

Public PoC
Published
25 October 2026
Modified
28 October 2026
Patch / advisory
CVSS Score v4 8.3
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0025 17th percentile
Risk Priority 37 floored blend · peak EPSS

CVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). EPSS, Forum of Incident Response and Security Teams (FIRST), epss.first.org. Risk Priority is our own derived reading, not an NVD score.

Summary

CVE-2026-116180 is a high-severity Use of Uninitialized Resource (CWE-908) vulnerability in Vllm. Its CVSS base score is 8.3 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 17th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)

Related Threats

MITRE ATT&CK Enterprise Techniques

MITRE ATT&CK v20.0

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
T1499.004 Application or System Exploitation Impact
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
T1189 Drive-by Compromise Initial Access
Adversaries may gain access to a system through a user visiting a website over the normal course of browsing.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-7141Same product: Vllm Vllm
CVE-2026-54234Same product: Vllm Vllm
CVE-2026-93592Same product: Vllm Vllm
CVE-2026-90553Same product: Vllm Vllm
CVE-2026-116175Same product: Vllm Vllm
CVE-2026-94622Same product: Vllm Vllm
CVE-2026-94627Same product: Vllm Vllm
CVE-2026-93436Same product: Vllm Vllm
CVE-2026-54236Same product: Vllm Vllm
CVE-2026-115915Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.8.5 — 0.31.0

Mitigating Controls

Mitigating Controls (NIST 800-53 r5)

Our mappings, made for this CVE.

Developer testing and evaluation (including static analysis) can find uses of uninitialized resources after they are coded.

Requiring documented development standards and tools can mandate initialization checks and safe patterns that stop the weakness from being introduced.

Engineering principles can require explicit resource initialization before use, structurally avoiding uninitialized access.

Mitigating Controls (NIST CSF 2.0)

Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→CSF cross-walk — links open the control.

PR.PS-06 mostly match
blocks

Secure SDLC activities such as static analysis and code review directly prevent use of uninitialized resources while also addressing many other weaknesses.

Mitigating Controls (ISO/IEC 27001:2022 Annex A)

Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→ISO cross-walk — links open the control.

finds

Security testing in development and acceptance can detect uninitialized resource usage through dynamic analysis and fuzzing.

prevents

Secure coding standards directly require explicit initialization of all variables and resources, substantially mitigating CWE-908.

References