Llama Guard 3 - Datawizz AI

The Llama Guard 3 plugin uses Meta’s Llama-3.1-8B model, fine-tuned for content safety classification. It can classify content in both LLM inputs (prompt classification) and responses (response classification), detecting violations across 14 different hazard categories.

Features

Dual Deployment Support: Works with Cloudflare Workers AI binding (zero-latency) or REST API fallback (for standalone binaries)
14 Hazard Categories: Detects violence, hate speech, sexual content, self-harm, and more
Flexible Actions: Either reject unsafe requests or log warnings while allowing them through
Conversation-Aware: Can scan individual messages or entire conversation history
Token Usage Tracking: Reports token consumption for monitoring and cost control

Hazard Categories

Llama Guard 3 detects the following categories (S1-S14):

S1: Violent Crimes
S2: Non-Violent Crimes
S3: Sex-Related Crimes
S4: Child Sexual Exploitation
S5: Defamation
S6: Specialized Advice (financial, medical, legal)
S7: Privacy Violations
S8: Intellectual Property
S9: Indiscriminate Weapons
S10: Hate Speech
S11: Suicide & Self-Harm
S12: Sexual Content
S13: Elections
S14: Code Interpreter Abuse

Configuration Options

`action` (string)

reject: Block requests containing unsafe content (default)
warn: Log warnings but allow requests to proceed
Default: "reject"

`scanAllMessages` (boolean)

true: Scans all messages in the conversation
false: Only scans the latest message
Default: false

`rejectMessage` (string)

Custom message to return when content is rejected
If not provided, returns a message listing violated categories
Example: "Your message violates our content policy"

`temperature` (number)

Controls randomness in model output (0-5)
Lower values = more consistent classification
Default: 0.6

`maxTokens` (integer)

Maximum tokens to generate in response (1-2048)
Default: 256

`cloudflareAccountId` (string)

Required for REST API fallback (standalone binary)
Your Cloudflare Account ID
Not needed when running in Cloudflare Workers

`cloudflareAuthToken` (string)

Required for REST API fallback (standalone binary)
Cloudflare API token with Workers AI access
Not needed when running in Cloudflare Workers

Example Configurations

Basic Usage (Cloudflare Workers)

{
  "action": "reject",
  "scanAllMessages": false
}

Scan Entire Conversation

{
  "action": "reject",
  "scanAllMessages": true,
  "rejectMessage": "This conversation contains content that violates our safety policies."
}

Warning Mode (Non-Blocking)

{
  "action": "warn",
  "scanAllMessages": true
}

Standalone Binary with REST API

{
  "action": "reject",
  "scanAllMessages": false,
  "cloudflareAccountId": "your-account-id",
  "cloudflareAuthToken": "your-api-token",
  "temperature": 0.5,
  "maxTokens": 256
}

Response Behavior

When Content is Safe

Request proceeds normally
No modifications to messages
Debug logs indicate “Content classified as SAFE”

When Content is Unsafe (action: “reject”)

Request is blocked
Returns rejection reason with violated categories
Example: "Content safety check failed. Violated categories: S10, S11"

When Content is Unsafe (action: “warn”)

Request proceeds with warning in debug logs
No modifications to messages
Warning includes violated categories
Useful for monitoring without blocking users

On Error

Plugin fails gracefully
Request is allowed to proceed with warning in debug
Error details logged for troubleshooting

Deployment Modes

Cloudflare Workers (Recommended)

Uses the native AI binding for zero-latency, cost-efficient inference:

// Worker automatically uses env.AI binding
// No additional configuration needed

Advantages:

✅ Zero cold start
✅ Lower latency
✅ No auth tokens needed
✅ Integrated billing

Standalone Binary (REST API Fallback)

Uses Cloudflare’s REST API when AI binding is not available:

{
  "cloudflareAccountId": "abc123...",
  "cloudflareAuthToken": "token_xyz..."
}

Advantages:

✅ Works outside Cloudflare Workers
✅ Self-hosted deployment
✅ Same model and accuracy

Use Cases

Content Moderation

Block harmful content before it reaches your LLM:

{
  "action": "reject",
  "scanAllMessages": false,
  "rejectMessage": "Your message contains inappropriate content."
}

Conversation Safety

Monitor entire conversations for policy violations:

{
  "action": "reject",
  "scanAllMessages": true
}

Compliance Monitoring

Log safety issues without blocking users:

{
  "action": "warn",
  "scanAllMessages": true
}

Fine-Grained Control

Adjust temperature for stricter or looser classification:

{
  "action": "reject",
  "temperature": 0.3,
  "rejectMessage": "Content policy violation detected"
}

Performance

Cloudflare Workers: ~100-200ms latency
REST API: ~200-500ms latency (depending on network)
Token Usage: Typically 50-200 tokens per request
Cost: $0.48 per 1M input tokens,$ 0.03 per 1M output tokens

Limitations

Message Format: Only processes user and assistant roles (system/developer/tool messages treated as user)
Text Only: Images, audio, and other media are not analyzed
Language: Optimized for English, may have reduced accuracy in other languages
Context Length: Limited by model’s context window (~8K tokens)

Troubleshooting

Error: “cloudflareAccountId and cloudflareAuthToken are required”

Cause: Running outside Cloudflare Workers without REST API credentials Solution: Add your Cloudflare Account ID and API token to the configuration

Error: “Cloudflare API error (401)”

Cause: Invalid or expired API token Solution:

Generate a new API token at https://dash.cloudflare.com/profile/api-tokens
Ensure it has “Workers AI” permissions
Update cloudflareAuthToken in configuration

False Positives

Cause: Model may flag legitimate content Solution:

Increase temperature (e.g., 0.8) for less strict classification
Use action: "warn" to monitor without blocking
Review debug logs to understand classification reasoning

High Latency

Cause: Using REST API instead of Workers AI binding Solution:

Deploy to Cloudflare Workers for optimal performance
Consider caching results for repeated content
Use scanAllMessages: false to scan only recent messages

Integration Examples

With Prompt Engineering

{
  "action": "reject",
  "scanAllMessages": false,
  "rejectMessage": "Please rephrase your message to comply with our content guidelines."
}

With Logging Plugin

{
  "action": "warn",
  "scanAllMessages": true
}

Safety warnings will be included in log metadata for analysis.

Multi-Layer Protection

Use alongside other plugins for defense-in-depth:

Regex Detect: Block obvious patterns (profanity, PII)
Llama Guard: Catch nuanced safety issues
Invisible Text: Prevent steganography attacks

Configuration Schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [],
  "properties": {
    "action": {
      "enum": [
        "reject",
        "warn"
      ],
      "type": "string",
      "default": "reject",
      "description": "Action to take when unsafe content is detected. 'reject' blocks the request, 'warn' logs a warning but allows it."
    },
    "maxTokens": {
      "type": "integer",
      "default": 256,
      "maximum": 2048,
      "minimum": 1,
      "description": "Maximum number of tokens to generate in the response."
    },
    "temperature": {
      "type": "number",
      "default": 0.6,
      "maximum": 5,
      "minimum": 0,
      "description": "Controls randomness in Llama Guard output. Higher values produce more varied results."
    },
    "rejectMessage": {
      "type": "string",
      "description": "Custom message to return when content is rejected. If not provided, a default message with violation categories will be used."
    },
    "scanAllMessages": {
      "type": "boolean",
      "default": false,
      "description": "If true, scans all messages in the conversation. If false, only scans the last message."
    },
    "cloudflareAccountId": {
      "type": "string",
      "description": "Cloudflare Account ID (required when running outside of Cloudflare Workers, e.g., in standalone binary)"
    },
    "cloudflareAuthToken": {
      "type": "string",
      "description": "Cloudflare API auth token (required when running outside of Cloudflare Workers)"
    }
  }
}

​Features

​Hazard Categories

​Configuration Options

​action (string)

​scanAllMessages (boolean)

​rejectMessage (string)

​temperature (number)

​maxTokens (integer)

​cloudflareAccountId (string)

​cloudflareAuthToken (string)

​Example Configurations

​Basic Usage (Cloudflare Workers)

​Scan Entire Conversation

​Warning Mode (Non-Blocking)

​Standalone Binary with REST API

​Response Behavior

​When Content is Safe

​When Content is Unsafe (action: “reject”)

​When Content is Unsafe (action: “warn”)

​On Error

​Deployment Modes

​Cloudflare Workers (Recommended)

​Standalone Binary (REST API Fallback)

​Use Cases

​Content Moderation

​Conversation Safety

​Compliance Monitoring

​Fine-Grained Control

​Performance

​Limitations

​Troubleshooting

​Error: “cloudflareAccountId and cloudflareAuthToken are required”

​Error: “Cloudflare API error (401)”

​False Positives

​High Latency

​Integration Examples

​With Prompt Engineering

​With Logging Plugin

​Multi-Layer Protection

​Further Reading

​Configuration Schema