Threats Tagged 'cve-2026-12491'
View all threats tagged with 'cve-2026-12491'. Filter and sort to focus on specific types of threats.
Stop chasing alerts. Route them.
Start free, then upgrade once to turn Radar into an automated delivery engine for your security stack.
Custom feeds / Automations: email, Slack, webhooks, SIEM/MISP / API access (baseline limits)
API access activates after upgrading in Console -> Billing.
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.
Filter Threats
Narrow down the results by type, severity, or affected countries
Threats Tagged 'cve-2026-12491'
Click on any threat for detailed analysis and mitigation recommendations
CVE-2026-12491: Misinterpretation of Input in Red Hat Red Hat AI Inference ServerCVE-2026-12491 0 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. Join the discussion | CVE Database V5 | 06/17/2026, 10:07:28 UTC Added: 06/17/2026, 11:08:40 UTC |
Showing 1 to 1 of 1 result