- CVSS
- HIGH · 8.8v3.1CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-03-27
- Weakness
- CWE-693, CWE-501
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-27893
Description
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.
References
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
- https://github.com/vllm-project/vllm/pull/36192
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
- https://access.redhat.com/errata/RHSA-2026:10140
- https://access.redhat.com/errata/RHSA-2026:10141
- https://access.redhat.com/errata/RHSA-2026:19712
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-27893 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.