CVE-2026-105755mediumCWE-639

CVE-2026-105755: falha de média gravidade em vllm-project vllm

vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

Publicada em · Atualizada em

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

13Vexday Risk Score

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

ssvc Trackcvss 4.2epss 0.2%
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L
Produtos afetados
vllm-project · vllm