Skip to content
Fencer Vulns
medium 6.5

CVE-2026-100654 json

vLLM before 0.29.0 Denial of Service via out-of-range stop_token_ids

published 2026-09-26 44 d ago modified 2026-10-07 32 d ago also EUVD-2026-87748

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 24%
public exploits
0
none known

Summary

vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).

Patch / fix

  • vllm-project vllm 0.29.0

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-100654 updated cvss 6.5

vllm: vLLM: Denial of Service via out-of-range stop token identifiers

  • Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-tpu-rhel9, rhaii/vllm-cuda-rhel9, rhaii/vllm-rocm-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, +7 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9, +1 more Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-th-torch-cuda-py312-rhel9, +1 more
    affected: workaround, no fix available “Avoid exposing these apis (/v1/completions and /v1/chat/completions) anonymously. Keeping the APIs behind API keys and authenticated clients is good.”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
40 d ago

Exploit prediction

0.31% chance of exploitation in the next 30 days, higher than 24% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 4.0 7.1 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CNA 4.0 7.1 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/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

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-129 Improper Validation of Array Index

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.