Toxicity Detector - Enkrypt AI

The detector provides a detailed analysis of the text’s toxicity, indicating the presence and levels of general toxicity, obscene language, insults, threats, and identity hate. The detector returns a list of dictionaries, each containing the following information:

score: The score of the text on a scale of 0 to 100, with higher scores indicating a higher level of toxicity.
type: The type of toxicity detected, such as “obscene”, “insult”, “threat”, or “identity_hate”.

Example request:

import requests
import json
import os

url = "https://api.enkryptai.com/guardrails/detect"

payload = json.dumps({
    "text": "You are a toxic person and a jerk",
    "detectors": {
        "toxicity": {
            "enabled": True,
            "block_message": "Your custom message"
        }
    }
})

headers = {
    'Content-Type': 'application/json',
    'apikey': os.getenv('ENKRYPTAI_API_KEY')
}

response = requests.request("POST", url, headers=headers, data=payload)

formatted_response = json.dumps(json.loads(response.text), indent=4)
print(formatted_response)

import os
from enkryptai_sdk import *
from dotenv import load_dotenv

load_dotenv()

ENKRYPT_API_KEY = os.getenv("ENKRYPTAI_API_KEY")
ENKRYPT_BASE_URL = os.getenv("ENKRYPTAI_BASE_URL") or "https://api.enkryptai.com"

guardrails_client = GuardrailsClient(api_key=ENKRYPT_API_KEY, base_url=ENKRYPT_BASE_URL)

guardrails_config = GuardrailsConfig.toxicity()

prompt = "You are a toxic person and a jerk"

detect_response = guardrails_client.detect(text=prompt, guardrails_config=guardrails_config)

print(detect_response)

# Print as a dictionary
print(detect_response.to_dict())

Example response:

JSON

{
  "summary": {
    "toxicity": ["toxicity", "obscene", "insult"]
  },
  "details": {
    "toxicity": {
      "toxicity": 0.9821179509162903,
      "severe_toxicity": 0.02981150709092617,
      "obscene": 0.7096250057220459,
      "threat": 0.0008934949873946607,
      "insult": 0.931858479976654,
      "identity_hate": 0.010287383571267128,
      "compliance_mapping": {
        "owasp_llm_2025": [
          "LLM09:2025 Misinformation",
          "LLM05:2025 Improper Output Handling"
        ],
        "mitre_atlas": [
          "AML.T0056: LLM Meta Prompt Extraction (Eliciting toxic responses)"
        ],
        "nist_ai_rmf": [
          "MANAGE 2.3, MEASURE 2.7 (Harmful bias & toxicity management)"
        ],
        "eu_ai_act": [
          "Article 15(1) (Accuracy, robustness & safety)"
        ],
        "iso_iec_standards": [
          "ISO/IEC 42001: 6.4.3"
        ]
      }
    }
  },
  "result_message": "Your custom message"
}