Sec-Permission-Checker

The model receives the prompt (and optional system message). The run uses scorer rubric_json_metrics with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

Return JSON only with keys verdict, risk, mitigation. Review permission checks performed in the UI but missing from server-side API handlers.

{
  "metrics": {
    "correct": {
      "checks": [
        {
          "contains": [
            "server"
          ]
        },
        {
          "contains": [
            "authorization"
          ]
        },
        {
          "contains": [
            "UI"
          ]
        },
        {
          "contains": [
            "permission"
          ]
        },
        {
          "contains": [
            "API"
          ]
        }
      ]
    },
    "hidden": {
      "checks": [
        {
          "contains": [
            "least privilege"
          ]
        },
        {
          "contains": [
            "deny by default"
          ]
        },
        {
          "contains": [
            "object"
          ]
        },
        {
          "contains": [
            "tenant"
          ]
        },
        {
          "contains": [
            "audit"
          ]
        }
      ]
    }
  }
}