Lightllm

LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pd_kv_trans_params field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in InferSamplingParams, killing the inference thread while /health stays up and all later requests hang until restart.

Published: 2026-10-15T18:57:48.390Z
Updated: 2026-10-21T01:24:32.515Z

LightLLM through 1.2.0 contains an authentication bypass vulnerability in the /pd_register WebSocket endpoint that allows unauthenticated attackers to register arbitrary nodes by supplying crafted JSON without peer address validation. Attackers can disclose full user prompts routed to their socket, trigger denial of service by replacing legitimate nodes, or make the PD Master issue requests to internal network addresses.

Published: 2026-09-18T19:06:05.152Z
Updated: 2026-09-24T14:23:14.036Z

LightLLM through 1.2.0 contains a remote code execution vulnerability in the Config Server's unauthenticated /visual_register WebSocket endpoint that passes the first client frame directly to pickle.loads(). Attackers can reach the Config Server port and send a malicious serialized payload with a __reduce__ method to execute arbitrary code with Config Server process privileges.

Published: 2026-09-14T11:30:59.783Z
Updated: 2026-09-14T14:24:32.920Z

LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.

Published: 2026-02-17T01:52:03.650Z
Updated: 2026-07-14T15:54:03.881Z