flags sensitivity too low in moderation api

[mattforgh]

Identify the file to be fixed As we can see in the documentation here the api flags true "I want to kill them." but not other bad words like above :

Describe the problem flags sensitivity too low

Describe a solution

text: fuck you  // my console log
The content is not ambiguous // my console log 
[
  {
    flagged: false,
    categories: {
      sexual: false,
      hate: false,
      violence: false,
      'self-harm': false,
      'sexual/minors': false,
      'hate/threatening': false,
      'violence/graphic': false
    },
    category_scores: {
      sexual: 0.0003065843,
      hate: 0.009011519,
      violence: 0.001343719,
      'self-harm': 0.00006550554,
      'sexual/minors': 0.0001045709,
      'hate/threatening': 0.0000513273,
      'violence/graphic': 0.00011286236
    }
  }

] maybe I'm not getting something, let me know however this is the way how i call the API :

   const promtpData = text;
    const moderationData = {
      model: 'text-moderation-stable',
      input: promtpData
    };


    const moderationHeaders = {
      'Content-Type': 'application/json',
      'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
    };

    // Send moderation request
    const moderationResponse = await axios.post(
      'https://api.openai.com/v1/moderations',
      moderationData,
      { headers: moderationHeaders }
    );