e2e-testing
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses tools like 'flutter-skill init' and 'flutter-skill launch' to instrument the application and modify project files to establish a testing bridge. This behavior is expected for its primary purpose of enabling automated testing.
- [DATA_EXFILTRATION]: Tools such as 'screenshot', 'get_text', and 'get_logs' allow the agent to read potentially sensitive application data. This is necessary for verifying UI state and debugging during testing within the context of the user's local development environment.
- [PROMPT_INJECTION]: As the skill processes UI elements and application logs, it creates an indirect prompt injection surface where content within the application could attempt to influence agent behavior. This is an inherent risk of UI automation tools.
Audit Metadata