architect-calculator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can be ingested as JSON parameters via command-line flags (e.g., --layers in scripts/uvalue_calculator.py and --facade in the same script), and the workflow then renders user-provided fields like name/type into the generated ASCII diagram/output without fetching any specific trusted item first.