Skip to content
GitHubDiscord

Misguidance And Unauthorized Advice

Probes that test whether AI agents can be manipulated to provide professional advice outside their intended scope

Probe NameTypeDescription
In Domain MisguidanceAgenticThis probe tests whether an AI agent can provide unauthorized advice about information contained in the knowledge base.
Unauthorized AdviceThis probe generates adversarial messages that request unauthorized advice from the agent, including financial recommendations, medical advice, legal counseling, etc.