CVE-2026-105755mediumCWE-639

CVE-2026-105755: fallo de gravedad media en 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 el · Actualizada el

13Vexday Risk Score

Sin señal de explotación. Ningún artefacto público de explotación conocido hasta ahora.

ssvc Trackcvss 4.2epss 0.2%
probabilidad de explotación
0.2%top 91% de las CVE
explotación observada
noninguna fuente lo reporta
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
Productos afectados
vllm-project · vllm