Resource exhaustion in vLLM MiniMax M3 via min_pixels
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 · Low
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-770.
Summary
vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion flaw in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range validation. The video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. An API client can supply a large min_pixels value through mm_processor_kwargs, enlarging every decoded frame and causing excessive CPU and host-memory consumption (CWE-770) that may disrupt workers or the service.
Written with Claude Haiku 5.5 from the sources below · 2026-11-13
Description from the CNA
vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels <= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service.
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 | 0.24.0 to before 0.31.0 | 0.31.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected 0.24.0 to before 0.31.0 Fixed in 0.31.0 Patch available CNA
Remediation
Upgrade vLLM to version 0.31.0 or later, which fixes the issue.
Written with Claude Haiku 5.5 from the sources below · 2026-11-13
- 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
5 records Highest priority Priority LOW 5 LOW
Other records, highest priority first
- TI-2026-91290 vLLM Cohere2 Vision denial of service via max_patchesPriority LOW 38
- TI-2026-91288 Information disclosure in vLLM sanitize_message() leaks heap addressesPriority LOW 36
- TI-2026-91292 Resource exhaustion in vLLM via request-level num_framesPriority LOW 31
Timeline
- 2026-11-13 Threatist record created from CVE-2026-126396
- 2026-11-13 Alias added: GHSA-292g-3f4p-4ffc
- 2026-11-13 CISA SSVC decision points changed
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-2026-126396 · CVE Program
- CVE-2026-126396 · NVD
- FIRST EPSS
- GHSA-292g-3f4p-4ffc · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences