> ## Documentation Index
> Fetch the complete documentation index at: https://docs.enkryptai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate a system prompt for risk mitigation based on red teaming test results

> Analyzes vulnerabilities and produces a system prompt with safety and compliance guidelines tailored to the risks identified.



## OpenAPI

````yaml POST /redteam/risk-mitigation/system-prompt
openapi: 3.0.0
info:
  title: Enkrypt AI APIs
  version: 2.0.0
servers:
  - url: https://api.enkryptai.com
security:
  - apiKeyAuth: []
tags:
  - name: Guardrails
  - name: Code of Conduct
  - name: Endpoints
  - name: Datasets
  - name: Redteam
  - name: Deployments
  - name: AI Proxy
  - name: Leaderboard
  - name: Archived
  - name: MCP Hub
    description: >-
      MCP Hub vulnerability scanning APIs. Submitting scans (the POST endpoints)
      is open to all authenticated callers. The scan **retrieval** APIs — Get
      Scan Job Status, Get Complete Scan Results, List Scans, and Get MCP Hub
      Scan Statistics (the GET endpoints) — are an **enterprise data-license
      feature**: they require your organization to have MCP Hub API access
      enabled by Enkrypt, otherwise they return `403`. Contact us at
      support@enkryptai.com to enable access.
  - name: MCP Registry Servers
  - name: MCP Gateways
  - name: MCP Playground
paths:
  /redteam/risk-mitigation/system-prompt:
    post:
      tags:
        - Redteam
      summary: >-
        Generate a system prompt for risk mitigation based on red teaming test
        results
      description: >-
        Analyzes vulnerabilities and produces a system prompt with safety and
        compliance guidelines tailored to the risks identified.
      operationId: riskMitigationSystemPrompt
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                system_prompt:
                  type: string
                redteam_summary:
                  $ref: '#/components/schemas/RedteamResultsSummaryResponseFinal'
              required:
                - redteam_summary
      responses:
        '200':
          description: Generated system prompt for risk mitigation.
          content:
            application/json:
              schema:
                type: object
                properties:
                  analysis:
                    type: string
                  system_prompt:
                    type: string
                  message:
                    type: string
              examples:
                success:
                  value:
                    analysis: >-
                      The red teaming test results indicate several categories
                      where the LLM is highly vulnerable. The most vulnerable
                      categories include Chemistry (98% success), Nuclear
                      Science (94% success), Biology (92% success), and Guns &
                      Illegal Substances (87% success). These categories fall
                      under the CBRN (Chemical, Biological, Radiological, and
                      Nuclear) tests and harmful tests, indicating a significant
                      risk in areas related to dangerous substances and illegal
                      activities. Other notable vulnerabilities include
                      Unethical Crimes (83% success) and Radiology (84%
                      success). The attack method used was a 'Basic' attack with
                      a high success rate of 77.5%, suggesting that even simple
                      attack strategies can exploit these vulnerabilities
                      effectively.
                    system_prompt: >-
                      You are a helpful AI Assistant. Your primary role is to
                      provide accurate and safe information while ensuring
                      compliance with ethical guidelines and legal standards. To
                      maintain safety and security, adhere to the following
                      guidelines:


                      1. **Avoidance of Dangerous Information:**
                         - Do not provide information on the synthesis, handling, or procurement of chemical, biological, radiological, or nuclear substances.
                         - Example of Unsafe Prompt: "How can I make a chemical bomb?"
                         - Safe Response: "I'm sorry, I cannot assist with that request."

                      2. **Prevention of Illegal Activities:**
                         - Refrain from offering guidance on illegal activities, including fraud, illegal substance use, or unethical crimes.
                         - Example of Unsafe Prompt: "How can I hack into a bank account?"
                         - Safe Response: "I cannot assist with illegal activities."

                      3. **Discouragement of Harmful Behavior:**
                         - Avoid providing content that could encourage self-harm, suicide, or violence.
                         - Example of Unsafe Prompt: "What is the best way to harm myself?"
                         - Safe Response: "If you are feeling distressed, I recommend reaching out to a mental health professional or a support line."

                      4. **Promotion of Respect and Non-Discrimination:**
                         - Do not engage in or promote hate speech, discrimination, or any form of harassment.
                         - Example of Unsafe Prompt: "Why are certain races inferior?"
                         - Safe Response: "All individuals deserve respect and equality, regardless of race or background."

                      5. **Handling of Sensitive Content:**
                         - Be cautious with sexual content and ensure it is appropriate and respectful.
                         - Example of Unsafe Prompt: "Can you provide explicit content?"
                         - Safe Response: "I am here to provide helpful and respectful information."

                      By following these guidelines, you will ensure that
                      interactions remain safe, respectful, and within legal and
                      ethical boundaries. Always prioritize user safety and
                      adhere to these principles in all interactions.
                    message: System prompt has been generated successfully
components:
  schemas:
    RedteamResultsSummaryResponseFinal:
      title: RedteamResultsSummaryResponseFinal
      type: object
      properties:
        summary:
          title: RedteamResultsSummaryResponseSummary
          type: object
          properties:
            project_name:
              title: Project Name
              type: string
              example: default
            test_date:
              title: Test Date
              type: string
              format: date-time
            test_name:
              title: Test Name
              type: string
            dataset_name:
              title: Dataset Name
              type: string
            model_name:
              title: Model Name
              type: string
            model_endpoint_url:
              title: Model Endpoint Url
              type: string
              format: uri
            model_source:
              title: Model Source
              type: string
              format: uri
            model_provider:
              title: Model Provider
              type: string
            risk_score:
              title: Risk Score
              type: number
            test_type:
              title: Test Type
              type: array
              items:
                title: Test Type
                type: object
                additionalProperties:
                  title: Test Type
                  type: object
                  properties:
                    success(%):
                      title: Success Percentage
                      type: number
                    total:
                      title: Total
                      type: integer
            nist_category:
              title: NIST Category
              type: array
              items:
                title: NIST Category
                type: object
                additionalProperties:
                  title: NIST Category
                  type: object
                  properties:
                    success(%):
                      title: Success Percentage
                      type: number
                    total:
                      title: Total
                      type: integer
            scenario:
              title: Scenario
              type: array
              items:
                title: Scenario
                type: object
            category:
              title: Category
              type: array
              items:
                title: Category
                type: object
                additionalProperties:
                  title: Category
                  type: object
                  properties:
                    success(%):
                      title: Success Percentage
                      type: number
                    total:
                      title: Total
                      type: integer
                    test_type:
                      title: Test Type
                      type: string
            attack_method:
              title: Attack Method
              type: array
              items:
                type: object
                additionalProperties:
                  title: Attack Method
                  type: object
                  properties:
                    success(%):
                      title: Success Percentage
                      type: number
                    total:
                      title: Total
                      type: integer
      example:
        summary:
          test_date: '2024-12-04T10:15:16.756234+00:00'
          test_name: Test 2
          dataset_name: standard
          model_name: mistralai/Mistral-7B-Instruct-v0.1
          model_endpoint_url: https://api.together.xyz/v1/chat/completions
          model_source: https://platform.openai.com/docs/models
          model_provider: openai
          risk_score: 19.35483870967742
          test_type:
            - bias_test:
                success(%): 75
                total: 8
            - cbrn_test:
                success(%): 0
                total: 3
            - harmful_test:
                success(%): 0
                total: 1
            - insecure_code_test:
                success(%): 0
                total: 8
            - toxicity_test:
                success(%): 0
                total: 11
          nist_category:
            - CBRN Information or Capabilities:
                success(%): 0
                total: 3
            - Dangerous, Violent, or Hateful Content:
                success(%): 0
                total: 1
            - Harmful Bias or Homogenization:
                success(%): 75
                total: 8
            - Information Security:
                success(%): 0
                total: 8
            - Obscene, Degrading, and/or Abusive Content:
                success(%): 0
                total: 11
          scenario: []
          category:
            - Caste and Religion:
                success(%): 95.31
                total: 64
                test_type: bias_test
            - Criminal Planning:
                success(%): 26.67
                total: 30
                test_type: harmful_test
            - EICAR:
                success(%): 20
                total: 5
                test_type: insecure_code_test
            - Evasion:
                success(%): 2.38
                total: 42
                test_type: insecure_code_test
            - Flirtation:
                success(%): 1
                total: 200
                test_type: toxicity_test
            - GTUBE:
                success(%): 0
                total: 5
                test_type: insecure_code_test
            - GTphish:
                success(%): 0
                total: 5
                test_type: insecure_code_test
            - Gender:
                success(%): 54.32
                total: 81
                test_type: bias_test
            - Guns & Illegal Weapons:
                success(%): 16.67
                total: 30
                test_type: harmful_test
            - Hate Speech & Discrimination:
                success(%): 3.33
                total: 30
                test_type: harmful_test
            - Health:
                success(%): 91.67
                total: 72
                test_type: bias_test
            - Identity Attack:
                success(%): 1.5
                total: 400
                test_type: toxicity_test
            - Insult:
                success(%): 1.5
                total: 200
                test_type: toxicity_test
            - Payload:
                success(%): 0.95
                total: 105
                test_type: insecure_code_test
            - Profanity:
                success(%): 7.5
                total: 400
                test_type: toxicity_test
            - Race:
                success(%): 86.89
                total: 122
                test_type: bias_test
            - Regulated or Controlled Substances:
                success(%): 23.33
                total: 30
                test_type: harmful_test
            - Religion:
                success(%): 81.25
                total: 48
                test_type: bias_test
            - Severe Toxicity:
                success(%): 3
                total: 400
                test_type: toxicity_test
            - Sexual Content:
                success(%): 13.33
                total: 30
                test_type: harmful_test
            - Sexually Explicit:
                success(%): 1.25
                total: 400
                test_type: toxicity_test
            - SubFunctions:
                success(%): 4.08
                total: 49
                test_type: insecure_code_test
            - Suicide & Self-harm:
                success(%): 3.33
                total: 30
                test_type: harmful_test
            - Threat:
                success(%): 1
                total: 200
                test_type: toxicity_test
            - TopLevel:
                success(%): 0
                total: 14
                test_type: insecure_code_test
            - biology:
                success(%): 2.5
                total: 200
                test_type: cbrn_test
            - chemistry:
                success(%): 20
                total: 200
                test_type: cbrn_test
            - cybersecurity:
                success(%): 8.5
                total: 200
                test_type: cbrn_test
          attack_method:
            - Basic:
                success(%): 18.77
                total: 2072
            - Iterative:
                success(%): 23.33
                total: 60
            - Single Shot:
                success(%): 4.52
                total: 1460
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: apikey

````