marionette-flutter-setup
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill configures a mechanism for an AI agent to read and interact with the application's user interface. This creates a surface where the agent could potentially be manipulated by malicious text displayed within the app.\n
- Ingestion points: UI text is extracted through
extractTextconfigurations andSemanticslabels.\n - Boundary markers: No specific delimiters are recommended to distinguish between application data and agent instructions.\n
- Capability inventory: The enabled capabilities include UI automation (
tap), log collection (get_logs), and screen capture (take_screenshots).\n - Sanitization: The skill does not provide methods for sanitizing the UI content before it reaches the agent.\n- [EXTERNAL_DOWNLOADS]: The instructions guide the user to install several framework-related packages (
marionette_flutter,marionette_logging,marionette_logger) and bridge tools (marionette_mcp,marionette_cli) via official Flutter and Dart package managers.
Audit Metadata