CVE-2026-105754

Published: Ott 06, 2026 Last Modified: Ott 06, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 6,5
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: none
Integrity: none
Availability: high

Description

AI Translation Available

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.

EPSS (Exploit Prediction Scoring System)

Trend Analysis

EPSS (Exploit Prediction Scoring System)

Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.

EPSS Score
0,0027
Percentile
0,2th
Updated

Single Data Point

Only one EPSS measurement is available for this CVE. Trend analysis requires multiple data points over time.

20

Improper Input Validation

Stable
Abstraction: Class Structure: Simple
Common Consequences
Security Scopes Affected:
Availability Confidentiality Integrity
Potential Impacts:
Dos: Crash, Exit, Or Restart Dos: Resource Consumption (Cpu) Dos: Resource Consumption (Memory) Read Memory Read Files Or Directories Modify Memory Execute Unauthorized Code Or Commands
Applicable Platforms
Technologies: AI/ML
Likelihood of Exploit: High
View CWE Details
617

Reachable Assertion

Draft
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Availability
Potential Impacts:
Dos: Crash, Exit, Or Restart
Applicable Platforms
Languages: Not Language-Specific, C, Java, Rust
View CWE Details
639

Authorization Bypass Through User-Controlled Key

Incomplete
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Access Control
Potential Impacts:
Bypass Protection Mechanism Gain Privileges Or Assume Identity
Applicable Platforms
All platforms may be affected
Likelihood of Exploit: High
View CWE Details
668

Exposure of Resource to Wrong Sphere

Draft
Abstraction: Class Structure: Simple
Common Consequences
Security Scopes Affected:
Confidentiality Integrity Other
Potential Impacts:
Read Application Data Modify Application Data Varies By Context
Applicable Platforms
All platforms may be affected
View CWE Details
704

Incorrect Type Conversion or Cast

Incomplete
Abstraction: Class Structure: Simple
Common Consequences
Security Scopes Affected:
Other
Potential Impacts:
Other
Applicable Platforms
Languages: C, C++, Not Language-Specific, Memory-Unsafe
View CWE Details
1284

Improper Validation of Specified Quantity in Input

Incomplete
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Other Integrity Availability
Potential Impacts:
Varies By Context Dos: Resource Consumption (Cpu) Modify Memory Read Memory
Applicable Platforms
All platforms may be affected
View CWE Details
https://github.com/vllm-project/vllm/commit/1970f3ed4be7fa8…
https://github.com/vllm-project/vllm/commit/1970f3ed4be7fa8620e4ddc4a12c36a8384…
https://github.com/vllm-project/vllm/pull/51898
https://github.com/vllm-project/vllm/pull/51898
https://github.com/vllm-project/vllm/releases/tag/v0.30.0
https://github.com/vllm-project/vllm/releases/tag/v0.30.0
https://github.com/vllm-project/vllm/security/advisories/GH…
https://github.com/vllm-project/vllm/security/advisories/GHSA-ph72-cqr5-qpp7