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…
X에서 속보 받기악용·대형 유출·장애를 대응 방법과 함께.
팔로우 @vulnpulse_app| CVE | CVE-2026-115914 |
|---|---|
| 정보원 | GitHub Advisory Database |
| 수집 시각 | 2026. 10. 29. 오전 09:48 |
| 데이터 | Markdown JSON |
2026. 10. 29. 오전 06:15, GitHub Advisory Database에서 "vLLM DeepSeek-OCR image processing vulnerable to denial of service"을(를) 게시했습니다 (유형: 취약점 권고). 심각도는 "보통"(medium)입니다. 관련 기술: Python. CVE: CVE-2026-115914.