CVE-2026-27893

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2026-27893
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-27893.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-27893
Aliases
Related
Published
2026-03-26T23:56:53.579Z
Modified
2026-07-16T03:30:55.043939193Z
Severity
  • 8.8 (High) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H CVSS Calculator
Summary
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
Details

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.

Database specific 
{
    "cwe_ids": [
        "CWE-693"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/27xxx/CVE-2026-27893.json",
    "cna_assigner": "GitHub_M"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Introduced
aab549870df50edf0512f0a59b574f692f546465
Fixed
bcf2be96120005e9aea171927f85055a6a5c0cf6
Fixed
00bd08edeee5dd4d4c13277c0114a464011acf72
Database specific 
{
    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
    "extracted_events": [
        {
            "introduced": "0.10.1"
        },
        {
            "fixed": "0.18.0"
        }
    ],
    "source": [
        "CPE_RANGE",
        "REFERENCES"
    ]
}

Database specific

source 
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-27893.json"