CVE-2026-34755

Description

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.

How to fix CVE-2026-34755

To remediate CVE-2026-34755, upgrade the affected package to a fixed version below.

• —upgrade to 0.19.0 or later
• —upgrade to 0.19.0 or later

Is CVE-2026-34755 being exploited?

Low — EPSS is 0.1%, meaning exploitation activity has not been observed at scale.

Affected packages (2)

• >= 0.7.0, < 0.19.0
• >= 0.7.0, < 0.19.0

CVSS scores

References (6)

• ADVISORYnvd.nist.gov/vuln/detail/CVE-2026-34755
• PATCHgithub.com/vllm-project/vllm
• WEBgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-144.yaml
• WEBgithub.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395