LLMHigh
CVE-2026-27893: vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1…
- Occurred
- Mar 27, 2026
- Published
- Mar 27, 2026
- Source
- NVD CVE
Summary
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 `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` 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.
Tags
- CVE
- CVE-2026-27893
- cvss:HIGH
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: CVE describes a critical security vulnerability in an LLM serving engine enabling remote code execution.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8