Resource exhaustion in vLLM via request-level num_frames
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-770.
Summary
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion flaw that lets inference clients bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. An authenticated remote attacker with low privileges can send a request with num_frames set to -1 or a large value along with many base64 JPEG frames, which forces the server to decode and stack all frames in memory and exhausts available memory (CWE-770).
Written with Claude Haiku 5.5 from the sources below · 2026-11-13
Description from the CNA
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- 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
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | 0.19.0 to before 0.31.0 | 0.31.0 | Patch available | CNA |
- vllm Vendorvllm-project Affected 0.19.0 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 flaw.
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-2026-91289 Resource exhaustion in vLLM MiniMax M3 via min_pixelsPriority LOW 37
- TI-2026-91288 Information disclosure in vLLM sanitize_message() leaks heap addressesPriority LOW 36
Timeline
- 2026-11-13 Threatist record created from CVE-2026-126399
- 2026-11-13 Alias added: GHSA-gm8j-8578-p8q4
- 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-2026-126399 · CVE Program
- CVE-2026-126399 · NVD
- FIRST EPSS
- GHSA-gm8j-8578-p8q4 · 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