The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted data from the mobile applications it interacts with during tests.
Ingestion points: The skill retrieves device state, including XML hierarchy, visible text, and screenshots, through the momentic_get_session_state tool.
Boundary markers: There are no explicit instructions or delimiters defined to separate the data retrieved from the mobile device from the agent's internal instructions.
Capability inventory: The agent has the capability to modify local test files (YAML), write to environment variables, and perform network operations via the axios helper in JavaScript steps.
Sanitization: The skill does not specify any sanitization or filtering protocols for content extracted from the mobile UI before it is interpreted by the agent.
[COMMAND_EXECUTION]: The skill instructs the agent to execute the npx momentic-mobile lint command to validate test syntax and configuration, which involves running a command-line utility within the project environment.
[REMOTE_CODE_EXECUTION]: The skill facilitates the execution of JavaScript code either inline (using the --code flag) or by loading local script files (e.g., ./scripts/mobile-utilities/setup.js) to perform assertions and data preparation.
[EXTERNAL_DOWNLOADS]: The use of npx momentic-mobile results in the download and execution of the vendor's utility package from the npm registry.

momentic-mobile-test