{"id":"CVE-2026-90553","title":"vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes","summary":"vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbi…","severity":"high","cvss":7.8,"cvssVector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","cwe":["CWE-94"],"vendor":"vllm","product":"vllm","affected":["vllm < 0.28.0"],"patched":["vllm 0.28.0"],"published":"2026-09-12","updated":"2026-09-16","sourceUpdated":"2026-09-16T17:31:40.200","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-90553","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor","label":"disclosure@vulncheck.com"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-90553.json"},{"url":"https://access.redhat.com/security/cve/CVE-2026-90553"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2532579"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-90553"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-90553"}],"tags":["nvd","cve.org","csaf","vex","red-hat","osv","pip"],"epss":0.00207,"epssPercentile":0.11118,"ssvc":{"exploitation":"none","automatable":"no","technicalImpact":"total","timestamp":"2026-09-14T18:25:25.303206Z"},"ingestedAt":"2026-09-14T15:23:07.479Z","aliases":["PYSEC-2026-3985","GHSA-3c86-2m5g-59q7"],"ecosystem":"pip","slug":"CVE-2026-90553","body":"## Overview\n\nvLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.\n\n## Affected\n\n- `vllm < 0.28.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.28.0`\n\n## Vendor advisories\n\n- **Red Hat VEX** · Important · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-09-16 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-90553.json)\n\n## Package advisory (CVE-2026-90553)\n\nAffected packages:\n\n- `vllm < 0.28.0`\n\nPatched in:\n\n- `vllm 0.28.0`\n\nSource: https://osv.dev/vulnerability/PYSEC-2026-3985","depth":"twilight","depthScore":43,"depthScoreParts":{"impact":42.9,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}