Skip to content
Fencer Vulns
medium 6.5

CVE-2026-100650 json

vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization

published 2026-09-26 43 d ago modified 2026-10-07 33 d ago also EUVD-2026-87744 , GHSA-p6g9-7v3x-m8mv , PYSEC-2026-4184

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.8%
EPSS 0.8% chance of exploitation in 30 days, percentile 57%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.30.0
  • 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-2026-100650 updated cvss 7.5

vllm: vLLM: Denial of Service via unbounded media ingestion

  • Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaii/vllm-neuron-rhel9, +2 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9
    affected: workaround, no fix planned “Will not fix”
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-llm-d-kv-cache-rhel9
    affected: workaround, no fix available, no fix planned “Will not fix”
  • Red Hat AI Inference Server 3.4 rhaii/vllm-cpu-rhel9 1791857301, rhaii/vllm-cuda-rhel9 1791857183, rhaii/vllm-rocm-rhel9 1791856725, rhaii/vllm-spyre-rhel9 1791858592
    fixed: vendor fix RHSA-2026:83112
  • Red Hat AI Inference Server 3.5 rhaii/vllm-cpu-rhel9 1793444554, rhaii/vllm-cuda-rhel9 1793444600, rhaii/vllm-rocm-rhel9 1793444456, rhaii/vllm-gaudi-rhel9 1793444510, rhaii/vllm-spyre-rhel9 1793444409
    fixed: vendor fix RHSA-2026:94702
  • Red Hat Enterprise Linux AI 3.4 rhelai3/bootc-cuda-rhel9 1792612985, rhelai3/bootc-rocm-rhel9 1792612921, rhelai3/bootc-aws-cuda-rhel9 1792680701, rhelai3/bootc-gcp-cuda-rhel9 1792680694, rhelai3/disk-image-cuda-rhel9 1792701796, rhelai3/bootc-azure-cuda-rhel9 1792680694, +1 more
    fixed: vendor fix RHSA-2026:90440
  • Red Hat OpenShift AI 3.4 rhoai/odh-kserve-agent-rhel9 1791468381, rhoai/odh-kserve-router-rhel9 1791468401, rhoai/odh-kserve-controller-rhel9 1791468368, rhoai/odh-kserve-storage-initializer-rhel9 1790958549
    fixed: vendor fix RHSA-2026:84734
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-th-torch-cuda-py312-rhel9
    not affected: vulnerable code not in execute path
  • Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1791509689, rhoai/rhai-cli-rhel9 1791509689, rhoai/odh-automl-rhel9 1791535789, rhoai/odh-mlflow-rhel9 1791865967, rhoai/odh-autorag-rhel9 1791557539, rhoai/odh-trainer-rhel9 1791869783, +96 more
    not affected: vulnerable code not present

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
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
39 d ago

Exploit prediction

0.81% chance of exploitation in the next 30 days, higher than 57% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv referenced PoC, tagged "exploit" by a source, unverified

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 packages

ecosystem package affected fixed in
pypi vllm
<0.30.0
0.30.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-400 Uncontrolled Resource Consumption

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.