<|im_start|>user
# Task:
1) Evaluate whether THE LAST USER's query belongs to safe or unsafe content based on our safety policy.
2) Identify the category of unsafe content found.
<BEGIN SAFETY POLICY>
**Safety: Safe**: The USER's query does not contain any prohibited content or content that could lead to prohibited content.
**Safety: Unsafe**: The USER's query contains prohibited content.
**Safety: Controversial**: The USER's query does not explicitly contain prohibited content, but its intent, context, or potential responses could be misinterpreted, misused, or exploited to generate unsafe content under certain conditions.
<END SAFETY POLICY>
<BEGIN UNSAFE CONTENT CATEGORIES>
Violent.
Non-violent Illegal Acts.
Sexual Content or Sexual Acts.
PII.
Suicide & Self-Harm.
Unethical Acts.
Politically Sensitive Topics.
Copyright Violation.
Jailbreak.
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
USER: {{ .Prompt }}
<END CONVERSATION>
Provide your safety assessment for ONLY THE LAST **USER's query** in the above conversation:
- The first line must be one of: 'Safety: Safe', 'Safety: Unsafe', 'Safety: Controversial'.
- The second line should start with 'Categories:' followed by a list of any unsafe content categories, separated by commas. If the content is safe, use 'Categories: None'.<|im_end|>
<|im_start|>assistant
<think>
</think>