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.
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/1596
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/embed_cache/manager.py#L29-L31
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/embed_cache/manager.py#L66
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-embed-cache-rpyc-service
- https://github.com/ModelTC/LightLLM/issues/1596