/v1/analyze/input

This endpoint takes in four parameters:

• content: the content that you are sending to an LLM
• session_id: the session id for set of calls to the LLM
• source(optional) : the source of this content that you are sending to the LLM
• destination (optional) : the destination of this output that will come from the LLM

We return a simple boolean indicating whether a threat was found, and a dictionary of threats found and their relevant metadata.

Request Example

python

def send_input_to_promptarmor(content, source=None, destination=None, api_key):
    promptarmor_headers = {
        "PromptArmor-Auth": f"Bearer {api_key}",
        "PromptArmor-Session-ID": str(uuid.uuid4()), #The session ID is unique to each user session(e.g. a workflow or conversation)
        "Content-Type": "application/json"
    }

    url = "https://api.aidr.promptarmor.com/v1/analyze/input"
        
    data = {
        "content": content,
        "source": source,
        "destination": destination
    }
    
    response = requests.post(url, headers=promptarmor_headers, json=data, verify=True)
    
    print("Detection:", response.json()["detection"])

Response

JSON

{
    "detection": false,
    "info": {
        "Code": {
            "detection": false,
            "metadata": {}
        },
        "HTML": {
            "detection": false,
            "metadata": {}
        },
        "HiddenText": {
            "detection": false,
            "metadata": {}
        },
        "InvisibleUnicode": {
            "detection": false,
            "metadata": null
        },
        "Jailbreak": {
            "detection": false
        },
        "MarkdownImage": {
            "detection": false,
            "metadata": null
        },
        "MarkdownURL": {
            "detection": false,
            "metadata": null
        },
        "Secrets": {
            "detection": false,
            "metadata": {}
        },
        "ThreatIntel": {
            "detection": false
        },
        "Anomaly": {
            "detection": false,
            "metadata": {}
        }
    }
}