NVIDIA Triton Inference Server是美国英伟达(NVIDIA)公司的一款开源软件,有助于标准化模型部署并在生产中提供快速且可扩展的 AI。 NVIDIA Triton Inference Server存在安全漏洞,该漏洞源于攻击者发送超大有效载荷可能导致栈溢出,可能导致拒绝服务。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 |
|---|---|---|---|---|
| NVIDIA | Triton Inference Server | All versions prior to 25.09 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2025-33186 | 8.8 HIGH | NVIDIA AIStore 信任管理问题漏洞 |
| CVE-2025-33178 | 7.8 HIGH | NVIDIA Nemo Framework 代码注入漏洞 |
| CVE-2025-23361 | 7.8 HIGH | NVIDIA Nemo Framework 代码注入漏洞 |
| CVE-2025-23357 | 7.8 HIGH | NVIDIA Megatron-LM 代码注入漏洞 |
| CVE-2025-33185 | 5.3 MEDIUM | NVIDIA AIStore 安全漏洞 |
No comments yet