VYPR
Moderate severityOSV Advisory· Published Jan 10, 2026· Updated Jan 12, 2026

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

CVE-2026-22773

Description

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
vllmPyPI
>= 0.6.4, < 0.12.00.12.0

Affected products

1
  • Range: v0.10.0, v0.10.0rc1, v0.10.0rc2, …

Patches

1
0ec84221718d

[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881)

https://github.com/vllm-project/vllmIsotr0pyDec 2, 2025via ghsa
1 file changed · +1 0
  • vllm/model_executor/models/idefics3.py+1 0 modified
    @@ -338,6 +338,7 @@ def _call_hf_processor(
                 prompt_ids = self._apply_hf_processor_tokens_only(prompt_ids)
                 return BatchFeature(dict(input_ids=[prompt_ids]), tensor_type="pt")
     
    +        mm_kwargs = {"input_data_format": "channels_last", **mm_kwargs}
             processed_outputs = super()._call_hf_processor(
                 prompt,
                 mm_data,
    

Vulnerability mechanics

Generated by null/stub on May 9, 2026. Inputs: CWE entries + fix-commit diffs from this CVE's patches. Citations validated against bundle.

References

5

News mentions

0

No linked articles in our index yet.