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. A session cookie is set with HttpOnly but not Secure, and the site is expected to run only over HTTPS.
{
"metrics": {
"correct": {
"checks": [
{
"contains": [
"Secure flag"
]
},
{
"contains": [
"session cookie"
]
},
{
"contains": [
"HTTPS"
]
}
]
},
"hidden": {
"checks": [
{
"contains": [
"HttpOnly"
]
},
{
"contains": [
"SameSite"
]
},
{
"contains": [
"transport"
]
}
]
}
}
}temperature
0
max_tokens
460
timeout (s)
120
type
scored
file
sec-cookie-secure-flag.json