vLLM 是一个用于大型语言模型的推理与服务引擎。在 0.32.0 版本之前,其兼容 OpenAI 的服务器默认将 Starlette 的 CORSMiddleware 配置为允许所有来源(即 allowed_origins 设置为通配符)。攻击者可利用恶意网页,通过受害者的浏览器访问位于本地主机、内网或 VPN 中的未认证 vLLM 服务器,调用包括 GET /v1/models 和 POST /v1/chat/completions 在内的接口,从而消耗 GPU 资源并读取响应内容。由于默认禁用了凭据,基于 C
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| vllm-project | vllm | < 0.32.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-115915 | 8.1 HIGH | vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE |
| CVE-2026-115912 | 7.5 HIGH | vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insec |
| CVE-2026-115911 | 6.5 MEDIUM | vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool |
| CVE-2026-115913 | 6.5 MEDIUM | vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a s |
| CVE-2026-115916 | 6.5 MEDIUM | vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device |
| CVE-2026-115914 | 6.5 MEDIUM | vLLM DeepSeek-OCR image processing vulnerable to denial of service |
| CVE-2026-115918 | 6.5 MEDIUM | vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs |