The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of test modules discovered on the filesystem to identify relevant tests and conditions. This creates an ingestion surface for untrusted data.
Ingestion points: Test modules located in the App's tests/ directory or a user-specified directory (SKILL.md).
Boundary markers: None specified; the skill does not explicitly instruct the agent to ignore instructions embedded within the test files.
Capability inventory: The skill executes commands through to-android-run and reads local files using rg (SKILL.md).
Sanitization: No sanitization or validation of the content within the test modules is described before processing.
[DYNAMIC_EXECUTION]: The skill dynamically identifies and executes code within local scripts.
Evidence: The workflow involves identifying functionName within absolute scriptPath modules and invoking them through the to-android-run interface (SKILL.md, Step 3).
[COMMAND_EXECUTION]: The skill utilizes system commands to browse and manage the filesystem.
Evidence: Uses rg --files (ripgrep) to recursively discover test files in the directory scope (SKILL.md, Step 2).

to-android-test