7.5
High
CVE-2026-5497 vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded…
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.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm-project/vllm 0.19 | earliest → < 0.19.0 | 0.19.0 |
| Red Hat AI Inference Server | Versions not published | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Versions not published | |
| Red Hat OpenShift AI (RHOAI) | Versions not published | |
| Red Hat Enterprise Linux AI 3.4 | Versions not published |
Other CVEs of vllm-project/vllm
The 4 CVEs of vllm-project/vllm →
CVE-2026-4944
vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in…
8.8
High
CVE-2024-11041
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function
9.8
Critical
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints
9.8
Critical