CVE-2026-27893

vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

State
Published
Severity
8.8 High
Published
Mar 26, 2026
Updated
Jul 27, 2026
Reserved
Feb 24, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.18.8 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HGitHub_M
3.18.8 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:Hredhat-SADP

Weaknesses

Affected Products

ProductVersions
vllmvllm-project
  • >= 0.10.1, < 0.18.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.