CVE Explore

Auth bypass in Vllm

CVE-2026-105754

CVSS v3
6.5 Medium
Public exploits
None known
EPSS
0.003 · 19.3th percentile
Published
2026-10-05

What to do

Fixed in
0.30.0
Affected
2 affected products

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Published · last modified .

CVSS v3 metric

CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.

Attack Vector
Network AV:N
Attack Complexity
Low AC:L
Privileges Required
Low PR:L
User Interaction
None UI:N
Scope
Unchanged S:U
Confidentiality
None C:N
Integrity
None I:N
Availability
High A:H

EPSS exploit prediction

EPSS 0.003, 19.3th percentile (last changed ); unchanged over 30 days. About EPSS.

Affected products

Weakness classification (CWE)

References