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 execute arbitrary code with service account privileges.
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/1610
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L11
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py#L138-L140
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-visual-only-rpyc-service
- https://github.com/ModelTC/LightLLM/issues/1610