7.5High

CVE-2026-5497Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

vllm-project vllm-project/vllm; Red Hat Red Hat AI Inference Server; Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3; Red Hat Red Hat OpenShift AI (RHOAI) Published: (5 months ago)

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.

Weakness (CWE): CWE-400CWE-770

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
Red Hat Red Hat AI Inference Server all versions
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 all versions
Red Hat Red Hat OpenShift AI (RHOAI) all versions
vllm vllm 0.8.0 – < 0.19.0
vllm-project vllm-project/vllm unspecified – < 0.19.0

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.8.0 < 0.19.0