CVE-2026-100651highCWE-400

CVE-2026-100651: falha de alta gravidade em vllm-project vllm

vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass

Publicada em · Atualizada em

Aviso por e-mail quando ela entrar no KEV, ganhar PoC pública ou subir de nota.

21Vexday Risk Score

Sem sinal de exploração. Nenhum artefato público de exploração conhecido até agora.

ssvc Trackcvss 7.1epss 0.4%
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:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Produtos afetados
vllm-project · vllm