CVE-2026-12491

Summary

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.

Affected Software

Weaknesses

• CWE-115: Misinterpretation of Input

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: none
  • Automatable: no
  • Technical Impact: partial

References

• https://access.redhat.com/security/cve/CVE-2026-12491
• https://bugzilla.redhat.com/show_bug.cgi?id=2489786

• ←Previous
• Next→