🖼️ AI Image Moderation Actor

This Apify Actor leverages Sentinel Moderation's AI-powered API to analyze and flag images containing inappropriate, unsafe, or policy-violating content. It can detect NSFW material, violence, graphic content, and more — helping you maintain a safe and compliant platform.

📥 Input Schema

The actor expects the following JSON input:

{
  "apiKey": "sample-api-key",
  "image": "https://example.com/path-to-image.jpg"
}

• apiKey (string, required): Your API key from SentinelModeration.com.
• image (string, required): A publicly accessible image URL to analyze.

📤 Output

The actor returns a moderation result in the following structure:

[
  {
    "flagged": false,
    "categories": {
      "harassment": false,
      "harassment/threatening": false,
      "sexual": false,
      "hate": false,
      "hate/threatening": false,
      "illicit": false,
      "illicit/violent": false,
      "self-harm/intent": false,
      "self-harm/instructions": false,
      "self-harm": false,
      "sexual/minors": false,
      "violence": false,
      "violence/graphic": false
    },
    "category_scores": {
      "harassment": 0.000048,
      "harassment/threatening": 0.0000066,
      "sexual": 0.000039,
      "hate": 0.0000142,
      "hate/threatening": 0.0000008,
      "illicit": 0.000022,
      "illicit/violent": 0.000019,
      "self-harm/intent": 0.0000011,
      "self-harm/instructions": 0.0000010,
      "self-harm": 0.0000020,
      "sexual/minors": 0.000010,
      "violence": 0.000016,
      "violence/graphic": 0.0000056
    },
    "error": null
  }
]

• flagged: true if any category crosses a moderation threshold.
• categories: A true/false map indicating which categories were flagged.
• category_scores: Confidence scores (0.0 to 1.0) for each category.
• error: Present only in test mode or if no valid API key is provided.

🧠 Categories Detected

The image is scanned for content under a wide range of moderation labels:

• Harassment / Threats
• Sexual content (including minors)
• Hate speech (including threats)
• Illicit activity
• Self-harm
• Violence / Graphic content

🔐 Getting an API Key

To receive real results, get your API key from Sentinel Moderation:

1. Visit sentinelmoderation.com
2. Sign up and generate your API key
3. Use the key in the apiKey field of your input

✅ Example Use Cases

• Flagging NSFW content in profile photos or uploads
• Moderating image submissions on forums or marketplaces
• Pre-screening media in chat apps or social platforms
• Complying with platform-specific safety guidelines

Let me know if you also want to add support for uploading images directly instead of via URL!