Fix log injection via unsanitized user input in RiskAdjustmentController

[Copilot]

Code scanning alert #805 flagged request.RiskModel — a user-controlled [FromBody] field — being passed unsanitized into a structured log call, enabling log injection via embedded CR/LF.

Change

RiskAdjustmentController.cs RequestScoreCalculation (line 176): wrap request.RiskModel with the existing SanitizeForLog() helper, consistent with all other user-input log parameters across both services.

// Before
_logger.LogInformation(
    "Score calculation requested for member {MemberId}, year {Year}, model {Model}",
    SanitizeForLog(request.MemberId), request.MeasurementYear, request.RiskModel);

// After
_logger.LogInformation(
    "Score calculation requested for member {MemberId}, year {Year}, model {Model}",
    SanitizeForLog(request.MemberId), request.MeasurementYear, SanitizeForLog(request.RiskModel));

All other string user-input log parameters in both RiskAdjustmentController and EncountersController were already correctly sanitized.

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

[Copilot]

Copilot wasn't able to review any files in this pull request.

[aurelianware]

@copilot are there any changes to make on this PR?

[Copilot]

@copilot are there any changes to make on this PR?

No further changes are needed. The PR is complete — request.RiskModel is now wrapped with SanitizeForLog() at line 176, resolving alert #805. A full audit of every _logger call in both RiskAdjustmentController and EncountersController confirms all user-supplied string values are already sanitized; the only other log args that aren't wrapped are numeric/enum types (int, decimal, LineOfBusiness, ScoreStatus) which don't carry injection risk.