CVE-2026-12491
MEDIUM 4.8A 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.
No known exploitation, public exploit, or elevated probability at this time. Track for changes.
Exploitation likelihood
0.2%chance of exploitation in 30 days · 15th percentile
Impact if exploited
4.8CVSS 3.1 · MEDIUM
- ConfidentialityNone
- IntegrityLow
- AvailabilityLow
What an attacker needs
- ✓Access: Reachable over the network — no local access needed
- ✓Privileges: No account or privileges required
- ✓User interaction: No user interaction needed
- ⚠Complexity: Needs a race window or specific setup
✓ lowers the bar for an attacker · ⚠ raises it
Affected
Vendors Red Hat
Products Red Hat Ai Inference Server Red Hat Enterprise Linux Ai (Rhel Ai) 3 Red Hat Openshift Ai (Rhoai)
Weakness (CWE)
- CWE-115
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L