Lucene search
+L

7 matches found

NVD
NVD
•added 2026/10/26 6:17 p.m.•22 views

CVE-2026-115915

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.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...

9.8CVSS0.0066EPSS
SaveExploits0References4
Mend
Mend
•added 2026/10/26 5:16 p.m.•25 views

CVE-2026-115915

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.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...

9.2CVSS7.6AI score0.0066EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2026/10/26 5:16 p.m.•41 views

CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE

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.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...

8.1CVSS0.0066EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/26 5:16 p.m.•30 views

CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE

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.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...

8.1CVSS6.2AI score
SaveExploits0References6
Vulnrichment
Vulnrichment
•added 2026/10/26 5:16 p.m.•4 views

CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE

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.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...

8.1CVSS7.6AI score0.0066EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/26 5:16 p.m.•77 views

CVE-2026-115915

The vLLM inference engine (prior to version 0.32.0 ) is vulnerable because ImageMediaIO passes attacker-controlled image bytes to Pillow via Image.open(BytesIO(data)) without restricting decoder selection or constraining formats via MIME labels. Attackers can submit specially crafted images, such...

9.8CVSS7.6AI score0.0066EPSS
SaveExploits0References4Affected Software1
CNNVD
CNNVD
•added 2026/10/26 12:00 a.m.•17 views

vLLM input validation error vulnerability

Versions of vLLM prior to 0.32.0 contain an input validation error vulnerability. This flaw arises because ImageMediaIO fails to restrict decoder selection and MIME tags do not enforce format constraints. Attackers can exploit this by sending image bytes under their control; these can then be...

9.8CVSS7.7AI score0.0066EPSS
SaveExploits0References4
Rows per page
Query Builder