Remote Code Execution Vulnerability in vLLM Inference Engine from vllm Project
CVE-2026-27893

8.8HIGH

Key Information:

Vendor

Vllm-project

Status
Vllm
Vendor
CVE Published:
26 March 2026

What is CVE-2026-27893?

The vLLM inference and serving engine for large language models has a significant security flaw impacting versions 0.10.1 through 0.17.9. Two specific model implementation files are configured to always trust remote code (trust_remote_code=True), overriding user-defined security settings (--trust-remote-code=False). This misconfiguration allows for potential remote code execution from malicious model repositories, even when users have opted out of trusting remote code. Users are advised to upgrade to version 0.18.0, which addresses this vulnerability and enhances security measures.

Human OS v1.0:
Ageing Is an Unpatched Zero-Day Vulnerability.

Remediate biological technical debt. Prime Ageing uses 95% high-purity SIRT6 activation to maintain genomic integrity and bolster systemic resilience.

Deploy the Patch

Affected Version(s)

vllm >= 0.10.1, < 0.18.0

References

https://github.com/vllm-project/vllm/security/advisories/...
x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/36192
x_refsource_MISC
https://github.com/vllm-project/vllm/commit/00bd08edeee5d...
x_refsource_MISC

CVSS V3.1

Score:
8.8
Severity:
HIGH
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
None
User Interaction:
Required
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

JSON
.