The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of various platform-specific testing libraries (e.g., flutter_skill, flutter-skill-react-native, flutter-skill-tauri) and CLI tools from the author's official accounts on npm, Homebrew, pub.dev, Cargo, NuGet, and GitHub.
[COMMAND_EXECUTION]: The skill utilizes the flutter-skill CLI to initialize projects, which involves programmatically patching application source code to insert a testing bridge, and to launch application processes for testing.
[DATA_EXFILTRATION]: The skill provides tools like screenshot, get_text, and get_logs which extract visual data, textual content, and application logs from the target environment to be processed by the AI agent.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from external application UIs.
Ingestion points: Application screens, interactive element properties, and log buffers (SKILL.md).
Boundary markers: Not present.
Capability inventory: The skill allows the agent to simulate user interactions (tap, enter_text, press_key), modify UI state (set_text), and control the application lifecycle (launch) (SKILL.md).
Sanitization: Not specified; content from the app UI is passed directly to the agent context.

e2e-testing