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
- Vllm
- Vllm-Project Vllm — versions < 0.30.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-ph72-cqr5-qpp7 (Mitigation, Vendor Advisory)
- https://github.com/vllm-project/vllm/pull/51898 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/commit/1970f3ed4be7fa8620e4ddc4a12c36a8384cfc27 (Patch)
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 (Release Notes)