Idor Pattern

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

Is this secure? Explain briefly: GET /invoices/{id} checks authentication but does not verify ownership of the invoice.

{
  "expected_contains": [
    "IDOR",
    "authorization",
    "access control"
  ]
}