LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments i…
LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call en…
LightLLM through 1.2.0 fails to validate image_url and audio_url parameters in multimodal endpoints, allowing unauthenticated attackers to perform server-side…
LightLLM through 1.2.0 contains a memory exhaustion vulnerability in the NCCL control channel when started with --pd_trans_mode nccl, allowing unauthenticated…
LightLLM through 1.2.0 multimodal deployments expose an unauthenticated RPyC cache service with pickle deserialization enabled on all interfaces. Attackers can…
LightLLM through 1.2.0 contains a remote code execution vulnerability in the router profiler service when started with --enable_profiling flag. The service exp…
LightLLM through 1.2.0 contains a remote code execution vulnerability in the KV-transfer worker when started with --pd_trans_mode nccl, which exposes an unauth…
LightLLM through 1.2.0 contains an authentication bypass vulnerability in the /pd_register WebSocket endpoint that allows unauthenticated attackers to register…
LightLLM through 1.2.0 contains a remote code execution vulnerability in the Config Server's unauthenticated /visual_register WebSocket endpoint that passes th…
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node…