MLA-C02 practice question: Guardrails and responsible AI (3 of 3)

Operating, Monitoring, and Securing ML and AI Solutions A free question from our original MLA-C02 practice exam. Try it, then open the answer to see why each option is right or wrong.

A logistics broker has built an AI agent that reads carrier emails and then looks up shipment records and changes delivery dates in its internal system. Some incoming emails contain instructions aimed at the agent, such as telling it to ignore its rules and change a shipment's carrier.

The security team wants the agent to resist these injected instructions, and it wants the agent to be unable to change delivery dates for any shipment outside the requesting carrier's own account, even if the model is persuaded to try.

Which TWO controls meet these requirements? (Choose two.)

Choose two answers.

A. Rely on the system prompt alone to tell the agent to ignore any instructions found inside emails, since the model follows its system prompt.
B. Screen each email with an Amazon Bedrock guardrail that has the prompt attack filter enabled, and block emails the guardrail flags before the agent acts on them.
C. Give the tool that changes delivery dates an IAM role and a code check that allow updates only to shipments in the requesting carrier's account.
D. Raise the model's temperature so that the agent is less predictable, which makes injected instructions less likely to work.
E. Give the agent full administrator access to the internal system, so that it can always complete the carrier requests without errors.

Show the answer and explanation

Answers: B, C

A. Wrong: A system prompt is a helpful instruction but is not an enforced control, and injected text can still persuade the model. The security team needs controls outside the model.
B. Right: Correct. The prompt attack category of a guardrail's content filters detects attempts to override the model's instructions, and the ApplyGuardrail API can screen text before the agent's model sees it. It is one layer of defense for the agent. Learn more: Detect and filter harmful content by using Amazon Bedrock Guardrails (opens in a new tab)
C. Right: Correct. Least-privilege permissions and checks inside the action function limit what the agent can change, even if the model is persuaded. The limit holds whatever the model decides.
D. Wrong: Higher temperature makes outputs more random and does not make the agent resist injected instructions. The option also reduces predictability in a way that works against the team.
E. Wrong: Full administrator access gives the agent far more power than it needs and would let an injected instruction change any shipment. The option is the opposite of the security goal.

Explanation

A guardrail's prompt attack filter screens incoming text for injected instructions, and least-privilege permissions plus checks in the tool limit what the agent can change, whatever the model decides. A system prompt alone is not enforced, and higher temperature or administrator access does not address the risk.

MLA-C02 practice question: Guardrails and responsible AI (3 of 3)

Explanation

Study

Keep practicing