LightLLM vulnerabilities
10 known vulnerabilities in LightLLM from ModelTC. 10 are rated high or critical. Each entry lists the affected versions and the release that fixes it, where the vendor has published one.
Latest first
- 7.5 High severity
LightLLM: Deserialization of Untrusted Data
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 parame
- 9.8 Critical severity
LightLLM: Deserialization of Untrusted Data
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __re
- 7.5 High severity
LightLLM: Missing Authentication for Critical Functionality
LightLLM through 1.2.0 mounts reinforcement learning control routes on the public HTTP API without authentication checks. Unauthenticated attackers can call endpoints like /pause_generation, /abort_request, /flush_cache, and /init_weights_update_group to disru
- 7.5 High severity
LightLLM: Allocation of Resources Without Limits or Throttling
LightLLM through 1.2.0 contains a memory exhaustion vulnerability in the NCCL control channel when started with --pd_trans_mode nccl, allowing unauthenticated attackers to exhaust KV-transfer worker memory. Attackers can call the exposed_set_value method to st
- 9.8 Critical severity
LightLLM: Deserialization of Untrusted Data
LightLLM through 1.2.0 multimodal deployments expose an unauthenticated RPyC cache service with pickle deserialization enabled on all interfaces. Attackers can send crafted serialized objects to exposed cache methods to execute arbitrary code with service priv
- 9.8 Critical severity
LightLLM: Deserialization of Untrusted Data
LightLLM through 1.2.0 contains a remote code execution vulnerability in the router profiler service when started with --enable_profiling flag. The service exposes an unauthenticated RPyC server with pickle deserialization enabled, allowing attackers to execut
- 9.8 Critical severity
LightLLM: Deserialization of Untrusted Data
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 unauthenticated RPyC control channel that deserializes attacker-supplied data. Attackers can send malicious
- 9.8 Critical severity
LightLLM: Missing Authentication for Critical Functionality
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 fu
- 9.8 Critical severity
LightLLM: Deserialization of Untrusted Data
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
- 9.3 Critical severity
LightLLM: Deserialization of Untrusted Data
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() w