It implements a simulation of the OWASP 2025 Top 10 for LLMs and Gen AI Apps risks. The tool automates attacks, captures logs, and generates an interactive HTML graph that visualizes the results.
SETUP
- Change the API endpoint to match the actual endpoint your model is listening to.
- Change input parameters to match what your API endpoint expects (to avoid 422 error).
EXECUTE
- To test without an actual application, execute
report_generator.py
. It will use sample data provided. - To run actual tests, execute
run_pipeline.py

