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

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

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.

N/A

未加控制的资源消耗(资源穷尽)

vLLM 资源管理错误漏洞

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.8.0版本及之后版本存在资源管理错误漏洞，该漏洞源于VideoMediaIO.load_base64方法中帧计数处理无限制，可能导致拒绝服务攻击。

N/A

N/A