ml-api-endpoint
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTION
Full Analysis
- [Dynamic Execution] (MEDIUM): The code uses
joblib.load('model.pkl')for model loading. Joblib utilizes pickle internally, which can execute arbitrary code if the loaded file is malicious. This poses an unsafe deserialization risk if the model file source is untrusted or can be modified by an attacker. Evidence:model = joblib.load("model.pkl")in the startup code block.
Audit Metadata