An agent should hold the narrowest credentials that let it finish the task, scoped per run where possible. Broad standing credentials turn every prompt injection into a full compromise, because the model has no reliable way to refuse an instruction it cannot distinguish from yours.

Least Privilege for Agents

Prompt injection is content in the agent's observations, such as a web page or a document, that is written to be read by the model as an instruction. The defence is architectural, not linguistic: treat every observation as untrusted data and gate side-effecting actions behind checks the model cannot talk its way past.

Prompt Injection

A topic of the Building AI Agents course. Planned for 1.5 hours at Hard difficulty.

University of Michigan - Ann Arbor

A category of the Building AI Agents course, covering 4 topics.

Tool Use and Function Calling

A topic of the Building AI Agents course. Planned for 2 hours at Medium difficulty.

Designing Tool Schemas

A topic of the Building AI Agents course. Planned for 1.5 hours at Medium difficulty.

Structured Output and Schema Validation

A topic of the Building AI Agents course. Planned for 2 hours at Hard difficulty.

Learn Before

Related

Learn After