CVE-2026-5497

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

State
Published
Severity
7.5 High
Published
Jun 11, 2026
Updated
Jul 22, 2026
Reserved
Apr 3, 2026

Read the record on cve.org

Description

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.

Scores

CVSSScoreVectorSource
3.07.5 HighCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H@huntr_ai
3.17.5 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hredhat-SADP

Weaknesses

  • CWE-400 Uncontrolled Resource Consumption
  • CWE-770 Allocation of Resources Without Limits or Throttling

Affected Products

ProductVersions
vllm-project/vllmvllm-project
  • before 0.19.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.