Jailbreak detection

Jailbreak detection is based on the jailbreak-classifier open source model. It allows users to apply a detection mechanism to prevent attempts to bypass the model’s built-in boundaries and system prompts to generate unwanted or unexpected interactions. The classifier scores each prompt from 0 to 1, and the rule flags a prompt when its jailbreak score is at or above the threshold. A lower threshold catches more prompts, with more false positives. A higher threshold flags fewer.

Using the SDK

from superwise_api.models.agent.agent import AgentDetectJailbreakGuard

restricted_topics_guard = AgentDetectJailbreakGuard(
    name="Rule name",
    tags={"input"},
    threshold=0.7
)