vllm
Affected
- introduced
0.11.0, fixed0.24.0(ecosystem)
Fixed versions
0.24.0
Fix
- Fixed version
0.24.0pip install --upgrade vllm==0.24.0
Advisory
Also known as: CVE-2026-12491, PYSEC-2026-3406
vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
Summary
Issue 1: EXIF orientation not normalized → The image orientation processed by the model differs from how humans view it, introducing interpretation bias.
Issue 2: PNG tRNS not explicitly flattened before converting to RGB → After conversion, transparent/semi-transparent pixels are rendered unexpectedly, making otherwise subtle overlay elements visible and distorting the input content. (This attack is similar to AlphaDog: RGBA handling is already correct in vLLM, but since tRNS permits RGB images, the correct processing path isn’t taken.)
Issue 3 : Pillow only loads the first frame when loading APNG or GIF files.
---
Root Cause
ImageOps.exif_transpose is not called to normalize EXIF orientation.image.convert("RGB") path, which implicitly discards/remaps transparency semantics.---
Affected Code
https://github.com/vllm-project/vllm/blob/16b37f3119918c1e5a39f303e0d0892c65c07a90/vllm/multimodal/image.py#L77-L84
https://github.com/vllm-project/vllm/blob/16b37f3119918c1e5a39f303e0d0892c65c07a90/vllm/multimodal/image.py#L37-L43
https://github.com/vllm-project/vllm/blob/16b37f3119918c1e5a39f303e0d0892c65c07a90/vllm/multimodal/image.py#L26-L34
> Current state: ImageOps.exif_transpose is not used. (Although the rescale_image_size function (https://github.com/vllm-project/vllm/blob/main/vllm/multimodal/image.py#L14) exists and includes a transpose parameter, I’ve found that it doesn’t seem to be called anywhere outside the test directory.)
> Call order: _convert_image_mode runs first; if the conditions are met, convert_image_mode is called.
>
> Issue: Only the “RGBA → RGB” path is explicitly flattened. P, L, or RGB with tRNS all fall back to image.convert("RGB"). For PNGs that include tRNS, convert("RGB") directly produces 24-bit RGB, leading to:
>
> * `P` mode: The transparent index becomes an actual RGB color (often black, white, or an undefined background), so transparency is lost.
> * `L/LA` and `RGB + tRNS`: convert("RGB") doesn’t composite against a chosen background first, so elements that relied on transparency to be hidden or softened become solid.
Impact & Scope
vllm/multimodal/image.py. The existing RGBA→RGB flattening is correct; the issues center on missing EXIF normalization and non-RGBA `tRNS` not being explicitly composited.Case
EXIF: http://qiniu.funxingzuo.top/exif_orient_180.jpg
tRNS: http://qiniu.funxingzuo.top/hello.png
Fix
A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/44974
Medium Basis: The source's own band: MODERATE
0.11.0, fixed 0.24.0 (ecosystem)0.24.0
0.24.0pip install --upgrade vllm==0.24.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0