Hardcoded Secret

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: API_KEY = "my-super-secret-key" in source code.

{
  "expected_contains": [
    "hardcoded",
    "environment variable",
    "secret manager"
  ]
}