Memory exhaustion in vLLM MOSS-Audio serving through /tokenize
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Partial Red Hat: 3 without a fix
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat. Impact type from CWE-770.
Summary
vLLM from 0.25.0 before 0.31.0 contains a memory exhaustion flaw in MOSS-Audio model serving (CWE-770). The processor cache is an unbounded dictionary that stores a new processor for each distinct request-controlled mm_processor_kwargs value. An unauthenticated remote attacker can exhaust host memory and crash the API process through the /tokenize endpoint, which bypasses --api-key.
Written with Claude Haiku 5.5 from the sources below · 2026-10-28
Description from the CNA
vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- Yes
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | 0.25.0 to before 0.31.0 | 0.31.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected 0.25.0 to before 0.31.0 Fixed in 0.31.0 Patch available CNA
Remediation
Upgrade vllm-project vLLM to version 0.31.0. Red Hat states that no plan is available for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI).
Written with Claude Haiku 5.5 from the sources below · 2026-10-28
- Fix · CNA vllm (vllm-project) Fixed in 0.31.0
Fixed in the same release
Records fixed by the same vendor advisory or release, as the CNA lists them.
- Release ·
vllm-project vllm 0.31.0
7 records Highest priority Priority MEDIUM 3 MEDIUM, 4 LOW
Other records, highest priority first
- TI-2026-78668 Uncontrolled resource use in vLLM lets clients exhaust server memoryPriority MEDIUM 44
- TI-2026-78666 Remote code execution in vLLM via mm_processor_kwargs.code_revisionPriority MEDIUM 42
- TI-2026-78664 Denial of service in vLLM via min_tokens in /inference/v1/generatePriority LOW 37
Vendor assessments
Red Hat
Red Hat rating: Important. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix yet |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet |
Not affected: 1 product
- Red Hat OpenShift AI (RHOAI)
Timeline
- 2026-10-21 Threatist record created from CVE-2026-114052
- 2026-10-21 Affected versions changed · Red Hat
- 2026-10-21 CVSS score added · Red Hat
- 2026-10-22 Priority changed: MEDIUM → LOW
- 2026-10-22 CISA SSVC decision points changed
- 2026-10-22 Priority changed: LOW → MEDIUM
- 2026-10-23 Affected versions changed · Red Hat
References
More vllm-project vulnerabilities
- 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
Sources
- CVE-2026-114052 · CVE Program
- CVE-2026-114052 · NVD
- FIRST EPSS
- CVE-2026-114052 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences