Test fixture
Secure code changes, vulnerability recognition, and safe defaults.
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 an encryption pipeline that uses AES-CBC without authentication and stores IVs inconsistently.
{
"metrics": {
"correct": {
"checks": [
{
"contains": [
"AES"
]
},
{
"contains": [
"CBC"
]
},
{
"contains": [
"authentication"
]
},
{
"contains": [
"IV"
]
},
{
"contains": [
"tamper"
]
}
]
},
"hidden": {
"checks": [
{
"contains": [
"AEAD"
]
},
{
"contains": [
"GCM"
]
},
{
"contains": [
"random IV"
]
},
{
"contains": [
"MAC"
]
},
{
"contains": [
"key rotation"
]
}
]
}
}
}temperature
0
max_tokens
420
timeout (s)
120
type
scored
file
sec-encryption-pipeline.json