CVE-2026-90553 json
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
published 2mo ago modified last mo. also EUVD-2026-76871 , GHSA-3c86-2m5g-59q7 , PYSEC-2026-3985
- cvss
- 7.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 23%
- public exploits
- 0
- none known
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 arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.
Patch / fix
- pypi vllm 0.28.0
- vllm-project vLLM 0.28.0
Is CVE-2026-90553 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerVendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-90553 updated cvss 7.8
vllm: vLLM: Remote Code Execution via LlavaOnevision2 processor ignoring trust_remote_code
-
Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-tpu-rhel9, rhaii/vllm-cuda-rhel9, rhaii/vllm-rocm-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, +7 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9, +1 moreaffected: workaround, no fix available, no fix planned “Will not fix”
-
Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9affected: workaround, no fix planned “Will not fix”
-
Red Hat OpenShift AI 3.4 rhoai/odh-kserve-agent-rhel9 1791468381, rhoai/odh-kserve-router-rhel9 1791468401, rhoai/odh-llm-d-kv-cache-rhel9 1791317861, rhoai/odh-kserve-controller-rhel9 1791468368, rhoai/odh-kserve-storage-initializer-rhel9 1790958549fixed: vendor fix RHSA-2026:84734
-
Red Hat OpenShift AI (RHOAI) rhoai/odh-th-torch-cuda-py312-rhel9not affected: component not present
-
Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1791509689, rhoai/rhai-cli-rhel9 1791509689, rhoai/odh-automl-rhel9 1791535789, rhoai/odh-mlflow-rhel9 1791865967, rhoai/odh-autorag-rhel9 1791557539, rhoai/odh-trainer-rhel9 1791869783, +95 morenot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- total
- Assessed
- last mo.
Exploit prediction
0.31% chance of exploitation in the next 30 days, higher than 23% of all scored CVEs (FIRST EPSS, 2026-11-11).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <0.28.0 |
0.28.0 |
Affected products
- vllm-project vLLM
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7
vendor-advisory, advisory
-
vulncheck.com
/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor
third-party-advisory, advisory
Sources
- CVE List CVE-2026-90553
- NVD CVE-2026-90553
- OSV PYSEC-2026-3985
- Maintainer advisory GHSA-3c86-2m5g-59q7
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
The maintainers of vllm-project/vllm published their own advisory on GitHub. Reviewed sources take precedence over it.