CVE-2026-27893 | vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

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.

Published: 2026-03-27 Last update: 2026-03-30 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-27893 is rated Low Risk (38.5/100): CVSS High severity, with low exploitation likelihood (EPSS 0.03%). Monitor for updates and reassess as exploit intelligence or EPSS changes.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-27893

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-03-27 — 0.03% —

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-27893

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.8 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.8 5.9 [email protected]

Weakness enumeration for CVE-2026-27893

GitHub Security Advisory for CVE-2026-27893

GHSA-7972-pg2x-xr59 · Severity: high · Ecosystem: pip — vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out

OS Trackers for CVE-2026-27893

vendor priority summary link
redhat high — https://access.redhat.com/security/cve/CVE-2026-27893

Affected software / configurations for CVE-2026-27893

Vendor Product Version Raw CPE
vllm vllm >= 0.10.1, < 0.18.0 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2026-27893

cvelogic Threat Intelligence