{"id":"CVE-2026-27893","title":"vLLM is an inference and serving engine for large language models (LLMs)","summary":"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…","severity":"high","cvss":8.8,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","cwe":["CWE-693","CWE-501"],"vendor":"vllm","product":"vllm","affected":["vllm >= 0.10.1, < 0.18.0"],"patched":["vllm 0.18.0"],"published":"2026-03-27","updated":"2026-07-08","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-27893","references":[{"url":"https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72","label":"security-advisories@github.com"},{"url":"https://github.com/vllm-project/vllm/pull/36192","label":"security-advisories@github.com"},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59","label":"security-advisories@github.com"},{"url":"https://access.redhat.com/errata/RHSA-2026:10140","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:10141","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:19712","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:19724","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:19725","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:24977","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:8746","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:8747","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/errata/RHSA-2026:8748","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://access.redhat.com/security/cve/CVE-2026-27893","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2452055","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json","label":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-27893"},{"url":"https://github.com/vllm-project/vllm"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml"},{"url":"https://access.redhat.com/errata/RHSA-2026:37275"}],"tags":["nvd","osv","pip"],"epss":0.01346,"epssPercentile":0.7018,"ingestedAt":"2026-07-08T13:51:10.434Z","aliases":["GHSA-7972-pg2x-xr59","PYSEC-2026-2297"],"ecosystem":"pip","slug":"CVE-2026-27893","body":"## Overview\n\nvLLM 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.\n\n## Affected\n\n- `vllm >= 0.10.1, < 0.18.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.18.0`\n\n## Package advisory (CVE-2026-27893)\n\nAffected packages:\n\n- `vllm >= 0.10.1, < 0.18.0`\n\nPatched in:\n\n- `vllm 0.18.0`\n\nSource: https://osv.dev/vulnerability/GHSA-7972-pg2x-xr59","depth":"twilight","depthScore":49,"depthScoreParts":{"impact":48.4,"likelihood":0.3,"exploitation":0,"ransomware":0},"changes":[]}