Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| vllm-project / vllm-project/vllm | affected unspecified before 0.19.0 |
CWE
CWE-400
References
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
ADP enrichment
No English description supplied.
A flaw was found in vLLM. An attacker can exploit this vulnerability by sending a specially crafted API request containing an excessive number of base64-encoded JPEG frames within a data URL. This unbounded processing of frames in the `VideoMediaIO.load_base64()` method leads to an Out-of-Memory (OOM) condition, causing the server to crash and resulting in a Denial of Service (DoS).