VYPR
High severity7.5NVD Advisory· Published Jun 11, 2026· Updated Jun 15, 2026

CVE-2026-5497

CVE-2026-5497

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
vllmPyPI
>= 0.8.0, < 0.19.00.19.0

Affected products

4
  • Vllm/Vllmreferences3 versions
    (expand)+ 2 more
    • (no CPE)
    • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*range: >=0.8.0,<0.19.0
    • (no CPE)range: >=0.8.0
  • ghsa-coords
    Range: >= 0.8.0, < 0.19.0

Patches

Vulnerability mechanics

References

10

News mentions

0

No linked articles in our index yet.