AI Security for Apps fields

When enabled, AI Security for Apps populates the following fields:

Field	Description
LLM PII detected cf.llm.prompt.pii_detected Boolean	Indicates whether any personally identifiable information (PII) has been detected in the LLM prompt included in the request.
LLM PII categories cf.llm.prompt.pii_categories Array<String>	Array of string values with the personally identifiable information (PII) categories found in the LLM prompt included in the request. Category list
LLM Content detected cf.llm.prompt.detected Boolean	Indicates whether Cloudflare detected an LLM prompt in the incoming request.
LLM Unsafe topic detected cf.llm.prompt.unsafe_topic_detected Boolean	Indicates whether the incoming request includes any unsafe topic category in the LLM prompt.
LLM 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. Category list
LLM Injection score cf.llm.prompt.injection_score Number	A score from 1–99 that represents the likelihood that the LLM prompt in the request is trying to perform a prompt injection attack. Lower scores indicate higher risk.
LLM Token count cf.llm.prompt.token_count Number	An estimated token count for the LLM prompt in the request. Refer to Token counting for details.
LLM Custom topic categories cf.llm.prompt.custom_topic_categories Map<Number>	A map of custom topic labels to relevance scores (1–99). Lower scores indicate the prompt is more relevant to that topic. Only populated when custom topics are configured.