vLLM DeepSeek-OCR image processing vulnerable to denial of service

影響: pip:vllm >= 0.11.1, < 0.32.0 → 0.32.0

Any vLLM deployment serving a model of the DeepSeek-OCR family — deepseek-ai/DeepSeek-OCR, deepseek-ai/DeepSeek-OCR-2, or baidu/Unlimited-OCR (whose UnlimitedOCRForCausalLM subclasses DeepseekOCRForCausalLM) — can be killed by a single unauthenticated chat request carrying an ordinary, schema-valid PNG image, under completely default server configuration. The image model's input validation contains a guard inherited from the upstream DeepSeek-OCR reference implementation: python vllm/model_exec…

在 GitHub Advisory Database 阅读

2026/10/29 06:15，GitHub Advisory Database 发布了“vLLM DeepSeek-OCR image processing vulnerable to denial of service”（类型：漏洞公告）。严重程度为“中危”（medium）。相关技术：Python。CVE：CVE-2026-115914。