CVE-2026-90553
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
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.
Attack profile
How easy it is to exploit
- Attack vector
- Local
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Passive
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
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.
- Record
CVE-2026-90553- CVSS 4.0
- 8.5 High
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 - CVSS 3.1
- 7.8 High
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2026-76871
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.
- Record
EUVD-2026-76871- CVSS 4.0
- 8.5 High
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 - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-rp86-qf3f-pqfc
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2...
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.
- Record
GHSA-rp86-qf3f-pqfc- CVSS 4.0
- 8.5 High
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 - CVSS 3.1
- 7.8 High
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-90553- CVSS 4.0
- 8.5 High
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 - CVSS 3.1
- 7.8 High
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
OSV
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
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.
- Record
CVE-2026-90553- CVSS 4.0
- 8.5 High
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 - Weakness
- CWE-94
- Updated
- 2026-11-02
OSVPYSEC-2026-3985
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.
- Record
PYSEC-2026-3985- CVSS 4.0
- 8.5 High
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 - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
vllmPyPI |
before 0.28.0, plus listed versions 0.0.10.1.00.1.10.1.20.1.3 Show 45 moreShow less0.1.40.1.50.1.60.1.70.10.00.10.10.10.1.10.10.20.11.00.11.10.11.20.12.00.13.00.14.00.14.10.15.00.15.10.16.00.17.00.17.10.18.00.18.10.19.00.19.10.2.00.2.10.2.1.post10.2.20.2.30.2.40.2.50.2.60.2.70.20.00.20.10.20.20.21.00.22.00.22.10.23.00.24.00.25.00.25.10.26.00.27.0 |
0.28.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-90553 is a high vulnerability (CVSS 8.5) in Vllm, published September 12, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.31%, the 23rd percentile. Fixed in vllm 0.28.0.
References
github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7
vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor
nvd.nist.gov/vuln/detail/CVE-2026-90553
Left out here: 45 versions. The JSON record has them.