flutter-slang-i18n

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/scan_dart_strings.py (invoked by Workflow step 4 via uv run python ... --root /path/to/flutter/project), the agent reads and ingests Dart source code from the target Flutter project (user-supplied/tenant files), which can contain outsider-authored free text, and then prints candidate string literals.