CVE-2026-27893
8.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | >= 0.10.1, < 0.18.0 | affected |
Weaknesses
- CWE-693: CWE-693: Protection Mechanism Failure
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: no
- Technical Impact: total
vllm: vLLM: Remote code execution due to hardcoded trust_remote_code setting
Additional References
- https://access.redhat.com/security/cve/CVE-2026-27893
- https://bugzilla.redhat.com/show_bug.cgi?id=2452055
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json
- https://access.redhat.com/errata/RHSA-2026:19724
- https://access.redhat.com/errata/RHSA-2026:19725
- https://access.redhat.com/errata/RHSA-2026:8748
- https://access.redhat.com/errata/RHSA-2026:8746
- https://access.redhat.com/errata/RHSA-2026:8747
- https://access.redhat.com/errata/RHSA-2026:10140
- https://access.redhat.com/errata/RHSA-2026:10141
- https://access.redhat.com/errata/RHSA-2026:24977
- https://access.redhat.com/errata/RHSA-2026:19712
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
- https://github.com/vllm-project/vllm/pull/36192
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.