GHSA-x8xr-mj9x-6h7w
Duplicate Advisory: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
Impact
## Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-8jr5-v98p-w75m. This link is maintained to preserve external references. ## Original 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.
An attacker can exploit this over the network, without logging in, without any action by a user. Specific conditions have to be met, which makes an attack harder. If it succeeds: low risk of data or systems being changed, low risk of outages.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | >= 0.11.0, <= 0.23.0 | none recorded |