CVE-2026-100651vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass
Updated under an hour ago ()
Does this affect you?
It affects vllm-project vllm and 1 other product. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.
- CVSS
- 6.5 MEDIUM (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weakness (CWE)
- CWE-400
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- VulnCheck
- NVD analysis
- Analyzed
- Record last updated
- Sep 28, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
vllm-project vllm vllm_project:vllm (from the name) | before 0.29.0; 0.29.0 not affected | CNA record |
vllm vllm vllm:vllm | before 0.29.0 | NVD |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9vendor-advisory, exploit
- https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-decoder-prompt-length-bypassthird-party-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.