CVE-2026-12491A flaw was found in vLLM, an open-source library for large language model inference.
Updated under an hour ago ()
Does this affect you?
It lists no affected products yet. Add what you run and Signals checks it as products are added.
No exploitation reported and no EPSS estimate yet.
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.
- CVSS
- 4.8 MEDIUM (v3.1, NVD)CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
- Weakness (CWE)
- CWE-115
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- Not given
- NVD analysis
- Awaiting Analysis
- Record last updated
- Jul 7, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
No affected products are listed yet.
References
- https://access.redhat.com/security/cve/CVE-2026-12491
- https://bugzilla.redhat.com/show_bug.cgi?id=2489786
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.