CVE-2026-27893
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to versio
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.
HIGH · CVSS 8.8
EPSS 0.00046
Schedule remediation
- CVSS base score ≥ 7.0
Sigma rules0
YARA rules0