CVE-2026-27893
vLLM is an inference and serving engine for large language models (LLMs).
Published Mar 27, 2026 · updated Jul 21, 2026 · vllm vllm
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode when loading sub-components, bypassing the user's explicit security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Mar 27, 2026 · NIST NVD
Detected
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode when loading sub-components, bypassing the user's explicit security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches
Jul 21, 2026 · NIST NVD
Updated
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode when loading sub-components, bypassing the user's explicit security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches
Affected
- cpe vllm/vllmversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-27893
Official CVE identifier
cve.org - NIST NVDVulnerability recordCVE-2026-27893
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode when loading sub-components, bypassing the user's explicit `--trust-remote-code=False
nvd.nist.gov