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.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | >= 0.6.4, < 0.12.0 | 0.12.0 |
Affected products
1Patches
10ec84221718d[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881)
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- github.com/advisories/GHSA-grg2-63fw-f2qrghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-22773ghsaADVISORY
- github.com/vllm-project/vllm/commit/0ec84221718d920c3f46da879cc354f94b8fb59eghsaWEB
- github.com/vllm-project/vllm/pull/29881ghsaWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qrghsax_refsource_CONFIRMWEB
News mentions
0No linked articles in our index yet.