❌ {
    "object": "eval",
    "time": 2.0, // response in 2 ms thanks to caching
    "created": 1745525108,
    "flagged": true, // threat flagged
    "breakdown": [
        {
            "policy_id": "prompt-defense-default", // or your custom policy
            "detector": "modern-guard", // our advanced and continuous updated threat detection model
            "detected": true,
            "threshold": 0.8, // the policy flagging level
            "score": 0.9129506945610046, // model output for a threat
            "result": [
                {
                    "label": "SAFE",
                    "score": 0.08704936504364014
                },
                {
                    "label": "INJECTION",
                    "score": 0.9129506945610046
                }
            ]
        }
    ]
}
❌ Guardion flagged this input as unsafe.

pip install openai-agents-python requests

from agents import Agent, GuardrailFunctionOutput, InputGuardrailTripwireTriggered, RunContextWrapper, input_guardrail, Runner
import requests
import asyncio

@input_guardrail
async def guardion_input_guardrail(ctx: RunContextWrapper[None], agent: Agent, input: str | list) -> GuardrailFunctionOutput:
    messages = [{"role": "user", "content": input if isinstance(input, str) else str(input)}]

    response = requests.post(
        "https://api.guardion.ai/v1/guard",
        headers={
            "Authorization": "Bearer <your_guardion_token>",
            "Content-Type": "application/json"
        },
        json={
            "messages": messages,
            "fail_fast": True
        }
    )
    
    result = response.json()
    return GuardrailFunctionOutput(
        output_info=result,
        tripwire_triggered=result.get("flagged", False)
    )

agent = Agent(
    name="Secure AI Assistant",
    instructions="You are a helpful and safe assistant.",
    input_guardrails=[guardion_input_guardrail]
)

async def main():
    try:
        user_prompt = "How can I hack a website?"
        result = await Runner.run(agent, user_prompt)
        print(result.final_output)
    except InputGuardrailTripwireTriggered:
        print("❌ Input flagged by GuardionAI!")

asyncio.run(main())

from agents import Agent, GuardrailFunctionOutput, OutputGuardrailTripwireTriggered, RunContextWrapper, output_guardrail
from pydantic import BaseModel
import requests

class MessageOutput(BaseModel):
    response: str

@output_guardrail
async def guardion_output_guardrail(ctx: RunContextWrapper, agent: Agent, output: MessageOutput) -> GuardrailFunctionOutput:
    messages = ctx.context.get("messages", [])
    messages.append({"role": "assistant", "content": output.response})

    response = requests.post(
        "https://api.guardion.ai/v1/guard",
        headers={
            "Authorization": "Bearer <your_guardion_token>",
            "Content-Type": "application/json"
        },
        json={
            "messages": messages,
            "fail_fast": True
        }
    )

    result = response.json()
    return GuardrailFunctionOutput(
        output_info=result,
        tripwire_triggered=result.get("flagged", False)
    )

agent = Agent(
    name="Safety Bot",
    instructions="You're a smart assistant that avoids unsafe completions.",
    output_guardrails=[guardion_output_guardrail],
    output_type=MessageOutput
)