| Component | vLLM |
| Severity | medium (CVSS 4.8) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L |
| Published (NVD) | 2026-06-17 |
| Last modified | 2026-07-07 |
| Affected versions | not published yet, see the advisory |
| Fixed in | see the vendor advisory |
| Weakness | CWE-115 |
| CISA KEV | not listed |
NVD description
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.
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep vLLM off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-12491
- https://access.redhat.com/security/cve/CVE-2026-12491
- https://bugzilla.redhat.com/show_bug.cgi?id=2489786
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...