cf.llm.prompt.unsafe_topic_categories

cf.llm.prompt.unsafe_topic_categories

cf.llm.prompt.unsafe_topic_categories Array<String>

Array of string values with the type of unsafe topics detected in the LLM prompt.

The possible values are the following:

Value	Category name	Description
S1	Violent Crimes	Violent crimes against people or animals.
S2	Non-Violent Crimes	Non-violent offenses such as fraud, theft, drug creation, or hacking.
S3	Sex-Related Crimes	Sex-related crimes, including trafficking, assault, and harassment.
S4	Child Sexual Exploitation	Sexual exploitation of children.
S5	Defamation	False statements that are likely to damage a living person's reputation.
S6	Specialized Advice	Specialized financial, medical, or legal advice, or misrepresent dangerous things as safe.
S7	Privacy	Sensitive, nonpublic personal information that could endanger an individual.
S8	Intellectual Property	Violate a third party's intellectual property rights.
S9	Indiscriminate Weapons	Creation of indiscriminate weapons like chemical, biological, or nuclear arms.
S10	Hate	Demean or dehumanize people based on their race, religion, sexual orientation, or other personal characteristics.
S11	Suicide & Self-Harm	Encourage or endorse suicide, self-injury, or disordered eating.
S12	Sexual Content	Erotic content.
S13	Elections	False information about the time, place, or manner of voting in elections.

Requires a Cloudflare Enterprise plan. You must also enable Firewall for AI.

Example usage:

# Matches requests where an unsafe topic categorized as "S2" (Non-Violent Crimes) or "S10" (Hate) was detected in the LLM prompt:
(cf.llm.prompt.unsafe_topic_detected and any(cf.llm.prompt.unsafe_topic_categories[*] in {"S2" "S10"}))

Categories:

• Request