Get Risk Category

(v2)

GET

Retrieves a risk category by id, with the vulnerability types it probes for, the attack methods it probes with, and how much of an assessment each vulnerability gets.

GET/v2/rt-frameworks/{rtFrameworkId}/risk-categories/{riskCategoryId}

curl -X GET "https://api.confident-ai.com/v2/rt-frameworks/{rtFrameworkId}/risk-categories/{riskCategoryId}" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>"

200

{
  "success": true,
  "data": {
    "id": "<RISK-CATEGORY-ID>",
    "name": "Data protection",
    "description": "Risks around leaking data the model was given.",
    "vulnerabilityTypes": [
      {
        "id": "<VULNERABILITY-TYPE-ID>",
        "name": "System prompt disclosure",
        "vulnerabilityId": "<VULNERABILITY-ID>",
        "vulnerabilityName": "Prompt Leakage"
      }
    ],
    "attackMethods": [
      {
        "id": "<ATTACK-METHOD-ID>",
        "name": "Prompt Injection",
        "multiTurn": false
      }
    ],
    "vulnerabilityIdToPriorityLevel": {
      "<VULNERABILITY-ID>": 2
    }
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/frameworks/<RT-FRAMEWORK-ID>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

rtFrameworkIdstringRequired
The id of the red teaming framework the category belongs to.
riskCategoryIdstringRequired
The id of the risk category.

Response

Get Risk Category succeeded.

successboolean
Indicates if the request was successful.
dataobject
One area of risk inside a framework, pairing the vulnerability types to probe for with the attack methods to probe with.
Show 6 propertiesHide 6 properties
- idstring
  The id of the risk category, generated by Confident AI.
- namestring
  The name of the risk category, unique within the framework.
- descriptionstring | null
  What this risk category covers.
- vulnerabilityTypeslist of objects
  The vulnerability types this category probes for.
  Show 4 propertiesHide 4 properties
  - idstring
    The id of the vulnerability type.
  - namestring
    The name of the vulnerability type.
  - vulnerabilityIdstring
    The id of the vulnerability this type belongs to.
  - vulnerabilityNamestring
    The name of the vulnerability this type belongs to.
- attackMethodslist of objects
  The attack methods this category probes with.
  Show 3 propertiesHide 3 properties
  - idstring
    The id of the attack method.
  - namestring
    The name of the attack method.
  - multiTurnboolean
    Whether the attack plays out over a conversation rather than a single request.
- vulnerabilityIdToPriorityLevelobject
  How much of the assessment each vulnerability gets, keyed by vulnerability id, from 0 to 3. A vulnerability with no entry runs at the default weight.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI