# CVE-2026-90553: vLLM LlavaOnevision2 processor remote code execution via trust_remote_code bypass

Source: https://junglewise.ai/threats/cve-2026-90553-vllm-llavaonevision2-processor-remote-code-execution-via-trust  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-12. Updated: 2026-09-26  
License: CC BY 4.0 with a link back

CVE-2026-90553 · Severity: high · CVSS 7.8 · Published 2026-09-12

vLLM is an open-source framework for large language model serving and inference optimization. The LlavaOnevision2 multimodal processor loader contains a security flaw that fails to properly respect the trust_remote_code safety setting, allowing attackers to execute arbitrary code when a user loads a crafted malicious model. This bypasses a key security boundary designed to protect against untrusted models.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-90553 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-90553 being exploited in the wild.

**How severe is CVE-2026-90553?** High severity, with a CVSS score of 7.8, published 12 September 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.28.0.

**Is there a fix for CVE-2026-90553?** Yes. vllm (PyPI): upgrade to 0.28.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-90553 attacked?** It is attacked with local access, in a software library.

**Am I affected by CVE-2026-90553?** Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.28.0 or later

  ```sh
  pip install "vllm>=0.28.0"
  ```


## Technical details

The vulnerability is a code injection flaw in vLLM's LlavaOnevision2 processor loader (_load_ov2_processor). The function calls transformers.dynamic_module_utils.get_class_from_dynamic_module() and passes a trust_remote_code parameter that is not accepted by that function—the parameter is silently swallowed into **kwargs and ignored. This causes the attacker-supplied processing_llava_onevision2.py and video_processing_llava_onevision2.py modules to be imported and executed unconditionally, even when trust_remote_code is explicitly set to False. The attack vector is local with required user interaction (loading the model). An attacker can achieve arbitrary code execution with the full authority of the vLLM process. The vulnerability is fixed in vLLM 0.28.0 and later.

## Affected products

- vLLM Project vLLM before 0.28.0

## Identifiers

- CVE-2026-90553
- PYSEC-2026-3985

## Timeline

- 2026-08-28: disclosed: GitHub Security Advisory GHSA-3c86-2m5g-59q7 published
- 2026-09-12: advisory: CVE-2026-90553 published
- 2026-09-12: patched: Fixed in vLLM 0.28.0

## References

- [https://github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7](https://github.com/vllm-project/vllm/security/advisories/GHSA-3c86-2m5g-59q7)
- [https://www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor](https://www.vulncheck.com/advisories/vllm-before-0.28.0-remote-code-execution-via-llavaonevision2-processor)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)