LightLLM 1.2.0 及更早版本在公共 HTTP API 上挂载了强化学习控制路由,但未进行身份验证检查。未经身份验证的攻击者可以调用诸如 、 、 和 等端点,从而干扰推理操作,并导致以 参数启动的部署中的工作进程陷入停滞状态。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-103395 | 9.8 CRITICAL | LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service |
| CVE-2026-103243 | 5.8 MEDIUM | LightLLM through 1.2.0 Server-Side Request Forgery via multimodal endpoints |
No comments yet