High-risk tools in Agentic Automl Platform
6 of the 14 tools in Agentic Automl Platform are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
evaluate_ffnExecuteevaluate_ffn
-
hyperparameter_searchExecuteRun GridSearchCV for a given model type. Returns best params and CV score.
-
train_ffnExecuteTrain a feedforward neural network on a cleaned tabular CSV.
-
train_lstmExecuteTrain a stacked LSTM for multivariate time series forecasting.
-
train_modelExecuteTrain a model on a cleaned dataset. Logs to MLflow. Returns train metrics and run_id.
-
train_transformerExecuteTrain a Transformer encoder for multivariate time series forecasting.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.