vllm-project · vLLM · published 2026-03-26
CVE-2026-27893vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
This month EPSS 1.4% with high severity (CVSS 8.8).
CVE-2026-27893 is not known to be exploited in the wild. EPSS estimates a 1.4% chance of exploitation in the next 30 days, higher than 73% of all CVEs. This vLLM vulnerability: CVSS 8.8 (v3.1), a successful attack gives total control of the component. Fixed upstream in vLLM 0.18.0. Patch in your normal monthly cycle.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.18.0.
Patch events
AI toolingvLLM
vLLM security release: 0.18.0
Upgrade to
0.18.0Why: EPSS 1.4% with high severity (CVSS 8.8).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 1.4% (73th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 8.8 (v3.1)CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.10.1, < 0.18.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.