generate_security_report
Compile a structured security report from clinical AI model evaluation results, marking untested sections as not evaluated and providing a deployment recommendation only when a Security Posture Score is supplied.
Instructions
Compose a structured security report from whichever tool outputs you have.
Pass the raw dict returned by any subset of run_fgsm,
run_boundary_attack, run_membership_inference,
assess_attack_coverage, check_rbac, score_audit_completeness,
score_compliance, and compute_sps. Sections you didn't run are
marked "not evaluated", never silently assumed to pass. A
deployment recommendation only appears if `sps` (compute_sps's
own output) is supplied -- it is never inferred from partial
results.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "generate_security_report"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sps | No | ||
| fgsm | No | ||
| rbac | No | ||
| boundary | No | ||
| compliance | No | ||
| attack_coverage | No | ||
| audit_completeness | No | ||
| membership_inference | No |