CVE-2026-12491
published 2026-06-17CVE-2026-12491: A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata…
PriorityP424medium4.8CVSS 3.1
AVNACHPRNUINSUCNILAL
EPSS
0.24%
15.3th percentile
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.
Affected
29 ranges· showing 25
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| rhaii | vllm-cpu-rhel9 | — | — |
| rhaii | vllm-cuda-rhel9 | — | — |
| rhaii | vllm-gaudi-rhel9 | — | — |
| rhaii | vllm-neuron-rhel9 | — | — |
| rhaii | vllm-rocm-rhel9 | — | — |
| rhaii | vllm-spyre-rhel9 | — | — |
| rhaii | vllm-tpu-rhel9 | — | — |
| rhaiis | vllm-cpu-rhel9 | — | — |
| rhaiis | vllm-cuda-rhel9 | — | — |
| rhaiis | vllm-neuron-rhel9 | — | — |
| rhaiis | vllm-rocm-rhel9 | — | — |
| rhaiis | vllm-spyre-rhel9 | — | — |
| rhaiis | vllm-tpu-rhel9 | — | — |
| rhelai3 | bootc-aws-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-rocm-rhel9 | — | — |
| rhelai3 | bootc-cuda-rhel9 | — | — |
| rhelai3 | bootc-gaudi-rhel9 | — | — |
| rhelai3 | bootc-gcp-cuda-rhel9 | — | — |
| rhelai3 | bootc-rocm-rhel9 | — | — |
| rhoai | odh-kserve-agent-rhel9 | — | — |
| rhoai | odh-kserve-controller-rhel9 | — | — |
| rhoai | odh-kserve-router-rhel9 | — | — |
| rhoai | odh-kserve-storage-initializer-rhel9 | — | — |
| rhoai | odh-llm-d-kv-cache-rhel9 | — | — |
CVSS provenance
nvdv3.14.8MEDIUMCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
cvelistv5v3.14.8MEDIUMCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
vendor_redhat4.8MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
CVEList
Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
cvelistv5·2026-06-17·CVSS 4.8
CVE-2026-12491 [MEDIUM] CWE-115 Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.
Timeline: 2026-06-17: Reported to Red Hat.; 2026-06-10: Made public.
Red Hat
vllm: vllm: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
vendor_redhat·2026-06-10·CVSS 4.8
CVE-2026-12491 [MEDIUM] CWE-115 vllm: vllm: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
vllm: vllm: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.
Package: rhaiis/vllm-cpu-rhel9 (Red Hat AI Inference Server) - Fix deferred
Package: rhaiis/vllm-cuda-rhel9 (Red Hat AI Inferen
No detection rules found.
No public exploits indexed.
2026-06-17
Published