CVE-2026-100651 vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass
Attackers can cause denial of service in vLLM by submitting overlong token IDs to multimodal endpoints, bypassing length validation checks.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-100651?
CVE-2026-100651 is a high-severity denial of service vulnerability in Vllm Vllm, published on 26 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
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.
Weakness: CWE-400
Which versions are affected by CVE-2026-100651?
It affects 1 product.
Products include Vllm Vllm.
How do I fix CVE-2026-100651?
Upgrade to a fixed version.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-100651 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-100651 exists.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-3mqx-f33v-vgp9, GHSA-g43f-v3gj-45x5, MINI-2v6j-5q34-3j32, MINI-472m-wvcf-f92x, MINI-xg3f-rf8r-fr69.