Description
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | 0.19.0 – < 0.31.0 | 0.31.0 |
Advisories 1
- WID-SEC-2026-4195 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Nov 12, 2026
References
- GitHub Security Advisory (GHSA-vxqj-p4gw-9h4c) vendor-advisory
- VulnCheck Advisory: vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames third-party-advisory