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 sending crafted serialized objects to the profiler command queue.
Weakness
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
Potential Mitigations
- Make fields transient to protect them from deserialization.
- An attempt to serialize and then deserialize a class containing transient fields will result in NULLs where the transient data should be. This is an excellent way to prevent time, environment-based, or sensitive variables from being carried over and used improperly.
Related Attack Patterns
References
- https://github.com/ModelTC/LightLLM
- https://github.com/ModelTC/LightLLM/issues/1597
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/profiler_service.py#L32-L34
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/profiler_service.py#L46-L50
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-router-profiler-rpyc-service
- https://github.com/ModelTC/LightLLM/issues/1597