CVE-2026-12491 — MEDIUM (4.8)

Vulnerability 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.

CVSS Score

4.8

MEDIUM

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L

Attack Vector

NETWORK

Attack Complexity

HIGH

Privileges Required

NONE

User Interaction

NONE

Scope

UNCHANGED

Confidentiality

NONE

Integrity

LOW

Availability

LOW

Related Weaknesses (CWE)

CWE-115

References

FAQ

What is CVE-2026-12491?

CVE-2026-12491 is a vulnerability with a CVSS score of 4.8 (MEDIUM). 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 transpare...

How severe is CVE-2026-12491?

CVE-2026-12491 has been rated MEDIUM with a CVSS base score of 4.8/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-12491?

Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.