{"id":"ghsa-ghsa-gq5q-89c7-vhvx","seq":2056926,"kind":"advisory","title":"vLLM DeepSeek-OCR image processing vulnerable to denial of service","url":"https://github.com/advisories/GHSA-gq5q-89c7-vhvx","permalink":"https://vulnpulse.app/items/ghsa-ghsa-gq5q-89c7-vhvx","summary":"影響: pip:vllm >= 0.11.1, < 0.32.0 → 0.32.0\nAny 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…","severity":"medium","techs":["python"],"cves":["CVE-2026-115914"],"tags":["GHSA-gq5q-89c7-vhvx","vllm"],"source":{"id":"ghsa","name":"GitHub Advisory Database"},"published_at":"2026-10-28T21:15:35.000Z","fetched_at":"2026-10-29T00:48:52.653Z"}