Vulnerability details
CVE-2026-27893
Red Hat AI Inference Servervllm-project vLLM
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
CVSS 3.1
8.8High
Official 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.
CVSS scores
| Score | Version | Source | Vector |
|---|---|---|---|
| 8.8High | 3.1 | CVEProject cvelistV5 (CNA) (GitHub_M) | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| 8.8High | 3.1 | CVEProject cvelistV5 (CNA) (redhat-SADP) | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected products
| Vendor | Product | Versions | Source |
|---|---|---|---|
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| Red Hat | Red Hat AI Inference Server | All | CVEProject cvelistV5 (CNA) |
| vllm-project | vLLM | >= 0.10.1, < 0.18.0 | CVEProject cvelistV5 (CNA) |
References and advisories
17- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/36192 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 x_refsource_MISC
- https://access.redhat.com/security/cve/CVE-2026-27893 vdb-entryx_refsource_REDHAT
- https://bugzilla.redhat.com/show_bug.cgi?id=2452055 issue-trackingx_refsource_REDHAT
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json x_sadp-csaf-vex
- https://access.redhat.com/errata/RHSA-2026:19724 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:19725 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:8748 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:8746 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:8747 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:10140 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:10141 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:42644 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:24977 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:37275 vendor-advisoryx_refsource_REDHAT
- https://access.redhat.com/errata/RHSA-2026:19712 vendor-advisoryx_refsource_REDHAT
Kolun on Telegram @kolunsec
Exploited CVEs, key news and a daily digest
Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.
Details
- Published
- 2026-03-27
- Last updated
- 2026-07-27
- State
- Published
- Assigner (CNA)
- GitHub_M
Exploit prediction (EPSS)
1.36%
Probability of exploitation in 30 days
72%
Percentile (among all CVEs)
SSVC assessment (CISA)
- Automatable
- No
- Exploitation
- None
- Technical impact
- Total
Weaknesses (CWE)
- CWE-693Protection Mechanism Failure
- CWE-501Trust Boundary Violation