cve.bz

CVE-2026-100650 vllm vllm: Uncontrolled Resource Consumption

7.1 highExploit referenceEPSS 0.8%Fix available

High (7.1) in vllm vllm. EPSS 0.8% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.30.0.

On this page
vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

Severity

CVSS 4.0

7.1 high
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

CVSS 3.1

6.5 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.8% (unchanged from 0.8% a week ago; 0.7% 30 days ago) estimated probability of exploitation activity in the next 30 days; 57th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-09-30. 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-400 Uncontrolled Resource Consumption
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-100650 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-100650?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-100650?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-2026-100650 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 vllmbefore 0.29.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
PYSEC-2026-4184PyPIvllm<0.30.00.30.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

This vulnerability is rated as an Important severity flaw because it can be triggered remotely without authentication to crash the inference service via resource exhaustion, completely disrupting model serving availability. In Red Hat Enterprise Linux AI and OpenShift AI environments, deployments hosting vLLM handle multi-modal requests or tokenization operations where input acquisition occurs prior to applying payload size constraints. Because excessive system memory and outbound bandwidth can be consumed before request rejection occurs, an adversary can exhaust container resources, though the flaw does not allow code execution or data exposure.

Red Hat's mitigation

Limit network exposure to the vLLM inference service and block outbound network connections from the serving host or container to prevent fetching untrusted external media:

1. Restrict inbound access using firewall rules so only trusted client networks or API gateways can reach the inference port (e.g., port 8000):

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

# firewall-cmd --zone=trusted --add-source=<TRUSTED_IP_OR_CIDR> --permanent

# firewall-cmd --reload

2. In OpenShift AI environments, apply a Kubernetes NetworkPolicy to the pod namespace to restrict ingress traffic strictly to authorized proxy pods, and apply an egress rule that blocks outbound internet access, preventing the service from downloading arbitrary remote media URLs.

3. Enforce maximum request body size limits on upstream reverse proxies or ingress controllers to drop oversized inline base64 payloads before forwarding requests to the inference backend.

Caveats:

Restricting egress traffic will prevent valid remote media references from being processed if external multi-modal inputs are expected. Modifying firewall rules or reloading network services may briefly interrupt active connections.

ProductPackageStateAdvisory
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1791857301Fixed 2026-10-14RHSA-2026:83112
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1791858592Fixed 2026-10-14RHSA-2026:83114
Red Hat AI Inference Server 3.4rhaii/vllm-cuda-rhel9:1791857183Fixed 2026-10-14RHSA-2026:83120
Red Hat AI Inference Server 3.4rhaii/vllm-rocm-rhel9:1791856725Fixed 2026-10-14RHSA-2026:83121
Red Hat AI Inference Server 3.5rhaii/vllm-cpu-rhel9:1793444554Fixed 2026-11-03RHSA-2026:94702
Red Hat AI Inference Server 3.5rhaii/vllm-rocm-rhel9:1793444456Fixed 2026-11-03RHSA-2026:94709
Red Hat AI Inference Server 3.5rhaii/vllm-spyre-rhel9:1793444409Fixed 2026-11-03RHSA-2026:94717
Red Hat AI Inference Server 3.5rhaii/vllm-gaudi-rhel9:1793444510Fixed 2026-11-03RHSA-2026:94721
Red Hat AI Inference Server 3.5rhaii/vllm-cuda-rhel9:1793444600Fixed 2026-11-03RHSA-2026:94738
Red Hat Enterprise Linux AI 3.4rhelai3/disk-image-cuda-rhel9:1792701796Fixed 2026-10-26RHSA-2026:90432
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-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Will not fix
Red Hat OpenShift AI (RHOAI)rhoai/odh-llm-d-kv-cache-rhel9Affected
12 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-2026-100650.

Attack patterns (CAPEC)

  • CAPEC-147 XML Ping of the Death Likelihood: Low · Severity: Medium
  • CAPEC-227 Sustained Client Engagement
  • CAPEC-492 Regular Expression Exponential Blowup

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON