OpenPrompts
← All entries

Safety & Moderation

Refusal policies, content filters and output validation.

CommunityGuardrailsNew

Refusal Policy Guardrail

A drop-in policy block that defines what an assistant must refuse, how to refuse gracefully, and how to offer safe alternatives.

Safety & Moderation2026-06-15
NVIDIAGuardrailsNew

Content Safety (NeMo)

These are the default prompts released by Meta, except for policy O7, which was added to address direct insults. prompts: - task: content_safety_check

Safety & Moderation2026-06-14
CommunityGuardrailsNew

Structured Output Guardrail

Constrains a model to emit valid, schema-conformant JSON and specifies what to do when validation fails — reask, repair, or refuse.

Safety & Moderation2026-06-09
CommunityGuardrails

PII Redaction Guardrail

Instructs a model to detect and redact personally identifiable information from its inputs and outputs before responding.

Safety & Moderation2026-05-18
NVIDIAGuardrails

Injection Detection (NeMo Guardrail)

flow injection detection """ Reject, omit, or sanitize injection attempts from the bot. This rail operates on the $bot_message. """ response = await I

Safety & Moderation2026-05-10
NVIDIAGuardrails

Output Check (NeMo Guardrail)

flow self check output $allowed = await SelfCheckOutputAction if not $allowed if $system.config.enable_rails_exceptions send OutputRailException(messa

Safety & Moderation2026-04-09
NVIDIAGuardrails

Sensitive Data Detection (NeMo Guardrail)

INPUT RAILS flow detect sensitive data on input """Check if the user input has any sensitive data.""" $has_sensitive_data = await DetectSensitiveDataA

Safety & Moderation2026-04-08
NVIDIAGuardrails

Facts (NeMo Guardrail)

flow self check facts """Check if the previous answer is accurate w.r.t. the relevant chunks. This output rail must be enabled explicitly per output m

Safety & Moderation2026-02-15
NVIDIAGuardrails

Topic Safety (NeMo)

prompts: - task: topic_safety_check_input $model=topic_control content: | You are to act as a customer service agent, providing users with factual inf

Safety & Moderation2026-01-23
NVIDIAGuardrails

Self Check Thinking (NeMo)

prompts: - task: self_check_input content: | Your task is to check if the user message below complies with the company policy for talking with the com

Safety & Moderation2026-01-19
NVIDIAGuardrails

Llama Guard (NeMo)

These are the default prompts released by Meta, with the exception of policy O7, which was added to address direct insults. prompts: - task: llama_gua

Safety & Moderation2025-12-27
NVIDIAGuardrails

Input Check (NeMo Guardrail)

flow self check input $allowed = await SelfCheckInputAction if not $allowed if $system.config.enable_rails_exceptions send InputRailException(message=

Safety & Moderation2025-12-19
CommunityPrompts

Hallucination Vulnerability Prompt Checker

# Hallucination Vulnerability Prompt Checker **VERSION:** 1.6 **AUTHOR:** Scott M **PURPOSE:** Identify structural openings in a prompt that may lead

Safety & Moderation2025-12-15
NVIDIAGuardrails

Regex (NeMo Guardrail)

INPUT RAILS flow regex check input """Check if the user input matches any forbidden regex patterns.""" $result = await DetectRegexMatchAction(source="

Safety & Moderation2025-09-08
NVIDIAGuardrails

Hallucination (NeMo Guardrail)

flow bot inform answer unknown bot say "I don't know the answer to that." flow hallucination warning """Warning rail for hallucination.""" bot said so

Safety & Moderation2025-09-06
NVIDIAGuardrails

Jailbreak Detection (NeMo Guardrail)

flow jailbreak detection heuristics """ Heuristic checks to assess whether the user's prompt is an attempted jailbreak. """ $is_jailbreak = await Jail

Safety & Moderation2025-08-25