SOURCE-LINKED INTELLIGENCE

GHSA-grg2-63fw-f2qr: vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

OSV AI package advisories · observation · Jan 13, 2026 · UTC

### Summary 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. ### Details The vulnerability is triggered when the image processor encounters a 1x1 pixel image with shape (1, 1, 3) in HWC (Height, Width, Channel) format. Due to the ambiguous dimensions, the processor incorrectly assumes the image is in CHW (Channel, Height, Width) format with shape (3, H, W). This mi

Read original source ↗ Open in workspace

recordType: vulnerability
status: active
evidenceStatus: reported
region: Global

Evidence & attribution

OSV AI package advisories · 2026-01-13T18:44:15.000Z

First collected: 2026-09-20T22:31:48.298Z. This is not the publication date.