CVE-2026-12491
What it is
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.
At a glance
- Exploitability
- Can be exploited over the network without logging in. Limited direct impact.
- Exploit odds
- 0.2% chance of exploitation in the next 30 days (EPSS).
- Fix
- No patch or advisory is linked yet. Look at mitigations or restrict exposure.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Why it ranks here
- Exploited in the wild: no, CISA does not list it.
- Exploit odds: 0.2% in the next 30 days (EPSS).
- Severity: 4.8 MEDIUM (CVSS).
- Fix: none linked yet, which raises it.
Details
- Published
- Last modified
- Exploit probability
- 0.2% · EPSS, next 30 days
- Weakness
- CWE-115
- Record status
- Awaiting Analysis
Attack profile CVSS 3.1 · 4.8
- Attack vector
- Network
- Complexity
- High
- Privileges needed
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- None
- Integrity
- Low
- Availability
- Low
Raw vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
Is it in your code?
Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.
Read https://cve-list.com/agent/cve/CVE-2026-12491.md and follow it. Check whether this project is affected by CVE-2026-12491. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.
