A platform team wants shift-left security for a new multi-agent claims workflow before the first production canary. They already run dependency scanning on infrastructure code. Which additional practice best targets agent-specific abuse paths such as prompt injection and tool misuse?
Select an answer to reveal the explanation.
Short Explanation
The correct answer is A. Shift-left for agents means adversarial testing of prompts, tools, and orchestrations before canary, and Foundry's AI Red Teaming Agent is built for that loop. Waiting until full prod is the opposite of shift-left. TLS expiry checks matter but do not catch prompt injection. Framework choice does not magically remove abuse paths.
Full Explanation
Option A is correct. Exam skills explicitly include shift-left security principles using the AI Red Teaming Agent in Foundry to probe multi-agent systems for issues such as prompt injection and unsafe tool use before broad release.
Option B is incorrect because post-rollout-only adversarial testing leaves early users exposed and violates shift-left intent.
Option C is incorrect because certificate hygiene is necessary infrastructure security but does not evaluate agent reasoning, tools, or orchestration abuse paths.
Option D is incorrect because frameworks provide building blocks; they do not replace adversarial evaluation of your prompts, tools, and policies.