A consumer platform's Foundry-hosted assistant is being reviewed before launch. The moderation team wants the content filtering configuration to catch both attempts to manipulate the model into ignoring its instructions and content that promotes self-harm, while still tolerating the ordinary casual rude language the team expects from a general audience. (Select TWO.) Which two actions should the team take when configuring the deployment's content filters?
Select all correct answers, then click Submit.
Short Explanation
You need to turn on the jailbreak risk category for prompt-injection and instruction-override attempts, and turn on the self-harm category for content encouraging self-harm. Don't crank the profanity filter to its strictest level, because that would block the casual rude language you want to tolerate. Don't disable all filters, because that would leave both real risks unguarded.
Full Explanation
The correct actions are enabling the jailbreak risk category and enabling the self-harm category. Enabling the jailbreak risk category specifically targets attempts to manipulate the model into bypassing its instructions, which is a distinct risk from offensive wording and needs its own filter to catch prompt-injection style attacks. Enabling the self-harm category flags and blocks content that encourages or promotes self-harm, directly addressing the second requirement the team named. Setting the profanity filter to its strictest level is incorrect because it would block the casual rude language the team explicitly said it wants to tolerate, over-filtering ordinary conversation and frustrating a general audience rather than addressing jailbreak attempts or self-harm content. Disabling all content filters is incorrect because it removes protection against both risks the team is trying to catch, leaving the assistant exposed to instruction-override attacks and self-harm content alike, which is the opposite of what a pre-launch review is meant to prevent. Because jailbreak attempts and self-harm content are separate categories with separate filtering controls, the team needs to enable both specific categories rather than adjusting a single blanket setting.