ModelTC

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…

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…

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 __reduce__ methods to…

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 privileges.

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 execute arbitrary code by…

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 pickled objects to…

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…

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…

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 disrupt inference…

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 store unbounded…

A weakness has been identified in ModelTC LightX2V up to 0.5.0. Affected is the function AutoTokenizer.from_pretrained of the file lightx2v/models/runners/cosmos3/cosmos3_runner.py of the component Tokenizer. This manipulation of the argument auto_map causes code injection. The…

LightLLM through 1.2.0 fails to validate image_url and audio_url parameters in multimodal endpoints, allowing unauthenticated attackers to perform server-side request forgery. Attackers can supply arbitrary URLs to fetch internal resources, with vision model processing…