cve.bz

CVE-2026-100652 vllm vllm: Improper Input Validation

8.2 highExploit referenceEPSS 0.4%Fix available

High (8.2) in vllm vllm. EPSS 0.4% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.24.0.

On this page
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

Severity

CVSS 4.0

8.2 high
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

CVSS 3.1

7.5 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS
0.4% (unchanged from 0.4% a week ago; 0.4% 30 days ago) estimated probability of exploitation activity in the next 30 days; 37th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: partial, assessed 2026-09-28. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-20 Improper Input Validation
OWASP Top 10
A05:2025 Injection
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-100652 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-100652?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-100652?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-100652 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
vllm-project vllmfrom 0.22.0 before 0.24.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
PYSEC-2026-4185PyPIvllm>=0.22.0 <0.24.00.24.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

This vulnerability is rated Important rather than Moderate because a remote, unauthenticated caller can crash the inference service with a single malformed generation request, resulting in a persistent denial of service. In Red Hat Enterprise Linux AI and OpenShift AI environments where vLLM exposes model serving endpoints over HTTP or gRPC, the frontend fails to validate stopping token identifiers against the active model vocabulary. When submitted with a minimum token threshold, these invalid values cause a fatal GPU execution failure that forces the entire inference engine offline until manually restarted, though the flaw cannot be leveraged for data compromise or code execution.

Red Hat's mitigation

Restrict network access to vLLM HTTP and gRPC service endpoints to trusted networks and authenticated clients only.

In host-based environments, restrict the serving port (typically TCP port 8000) using firewalld:

```

firewall-cmd --permanent --zone=trusted --add-source=<trusted_ip_or_subnet>

firewall-cmd --permanent --zone=public --remove-port=8000/tcp

firewall-cmd --reload

```

In Red Hat OpenShift AI deployments, apply a Kubernetes NetworkPolicy to the model-serving namespace to ensure only authorized ingress controllers or trusted application pods can reach the inference containers.

Warning: Reloading firewall rules with `firewall-cmd --reload` applies changes immediately and may interrupt active network connections.

Caveats: Network-level controls limit exposure to external untrusted callers, but they do not protect against crafted requests submitted by authorized users or internal services that consume the inference API.

ProductPackageStateAdvisory
Red Hat OpenShift AI 3.4rhoai/odh-kserve-agent-rhel9:1791468381Fixed 2026-10-19RHSA-2026:84734
Red Hat OpenShift AI 3.4rhoai/odh-kserve-controller-rhel9:1791468368Fixed 2026-10-19RHSA-2026:84734
Red Hat OpenShift AI 3.4rhoai/odh-kserve-router-rhel9:1791468401Fixed 2026-10-19RHSA-2026:84734
Red Hat OpenShift AI 3.4rhoai/odh-kserve-storage-initializer-rhel9:1790958549Fixed 2026-10-19RHSA-2026:84734
Red Hat AI Inference Serverrhaiis/vllm-cpu-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-cuda-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-rocm-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-rocm-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-rocm-rhel9Affected
7 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-100652.

Attack patterns (CAPEC)

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-20 (51).

References

Check your stackJSON