CVE-2026-5497 PUBLISHED

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

Assigner: @huntr_ai
Reserved: 03.04.2026 Published: 11.06.2026 Updated: 11.06.2026

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the VideoMediaIO.load_base64() method. When processing video/jpeg data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

Metrics

CVSS Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS Score: 7.5

Product Status

Vendor vllm-project
Product vllm-project/vllm
Versions
  • affected from unspecified to 0.19.0 (excl.)

References

Problem Types

  • CWE-400 Uncontrolled Resource Consumption CWE