CVE-2026-105757
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, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.
20
Improper Input Validation
StableCommon 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
248
Uncaught Exception
DraftCommon Consequences
Security Scopes Affected:
Availability
Confidentiality
Potential Impacts:
Dos: Crash, Exit, Or Restart
Read Application Data
Applicable Platforms
Languages:
C++, Java, C#
755
Improper Handling of Exceptional Conditions
IncompleteCommon Consequences
Security Scopes Affected:
Other
Potential Impacts:
Other
Applicable Platforms
All platforms may be affected
https://github.com/vllm-project/vllm/commit/c55e15a44ec4127832d4a86928a356fdd9e…
https://github.com/vllm-project/vllm/pull/51450
https://github.com/vllm-project/vllm/releases/tag/v0.30.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-85xf-c7hm-whqw