CVE•Published 2026-10-25•Modified 2026-10-28•0 articles on news•4 live references•NVD data

CVE-2026-116180Vllm · Vllm

Vulnerability data via NVD (ingested)

CVSS v3.1

7.7

HIGH

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H

EPSS percentile

Exploit Prediction Scoring System · top 84% of all CVEs

Weaknesses (CWE)

CWE-908Use of Uninitialized Resource

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.

Timeline

Published 2026-10-25

Modified 2026-10-28

External references

NVD MITRE GitHub PoC VulnCheck

Search for exposed instances

Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).

Shodan · vuln tag0 hosts

vuln:CVE-2026-116180

Hosts Shodan has explicitly fingerprinted as vulnerable.

Shodan · product

product:"Vllm Vllm"

All exposed Vllm Vllm instances — cross-reference with the CVE's affected-version range.

Shodan · banner/body mention

http.html:"Vllm"

HTTP body or banner mentions "Vllm" — catches deploys Shodan didn't identify as a product.

More intel sources (5)

Shodan report

vuln:CVE-2026-116180