CVE-2026-34755
בינונית 6.5
תיאור (מקור, אנגלית)
vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
מדדים
- CVSS 3.1
-
6.5 (MEDIUM)
מקור הציון: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H - EPSS — סבירות ניצול
- 1% (אחוזון 100) נכון ל-24/9/2026
- CWE
- CWE-770
מוצרים מושפעים
vllm: vllm
קישורים
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p PatchVendor Advisory
- https://access.redhat.com/errata/RHSA-2026:36005
- https://access.redhat.com/errata/RHSA-2026:36006
- https://access.redhat.com/errata/RHSA-2026:57380
- https://access.redhat.com/errata/RHSA-2026:57387
- https://access.redhat.com/errata/RHSA-2026:57389
- https://access.redhat.com/errata/RHSA-2026:57390
- https://access.redhat.com/errata/RHSA-2026:59144
- https://access.redhat.com/errata/RHSA-2026:59151
- https://access.redhat.com/security/cve/CVE-2026-34755