Read the docs
TI-2026-40172 Aliases CVE-2026-55646GHSA-v82g-2437-67m2

vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

Priority MEDIUM 62CWE-400Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-400.

Summary

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00519 44th percentileScored 2026-11-07
Fix Fixed vllm (vllm-project): 0.24.0vllm (PyPI): 0.24.0

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllm0.22.0 to before 0.24.00.24.0Patch availableCNA
—vllm (PyPI)0.22.0 to before 0.24.00.24.0Patch availableGHSA-v82g-2437-67m2
  • vllm Vendorvllm-project Affected 0.22.0 to before 0.24.0 Fixed in 0.24.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.22.0 to before 0.24.0 Fixed in 0.24.0 Patch available GHSA-v82g-2437-67m2

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.22.0 to before 0.24.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.22.0 to before 0.24.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.24.0
  • Fix · GHSA-v82g-2437-67m2 vllm (PyPI) Fixed in 0.24.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

Not affected: 3 products
  • Red Hat AI Inference Server
  • Red Hat Enterprise Linux AI (RHEL AI) 3
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-55646
  2. 2026-10-03 Alias added: GHSA-v82g-2437-67m2

References

Patch 2

Advisory 2

Other 2

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences