Upstream information
Description
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process's privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0.SUSE information
Overall state of this security issue: Does not affect SUSE products
This issue is currently rated as having critical severity.
| CVSS detail | CNA (GitHub) | National Vulnerability Database |
|---|---|---|
| Base Score | 8.1 | 9.8 |
| Vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| Attack Vector | Network | Network |
| Attack Complexity | High | Low |
| Privileges Required | None | None |
| User Interaction | None | None |
| Scope | Unchanged | Unchanged |
| Confidentiality Impact | High | High |
| Integrity Impact | High | High |
| Availability Impact | High | High |
| CVSSv3 Version | 3.1 | 3.1 |
SUSE Timeline for this CVE
CVE page created: Tue Oct 27 21:53:35 2026CVE page last modified: Thu Oct 29 18:01:02 2026