The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands such as pnpm dev, nohup, and lsof to manage the local application environment and monitor network ports during development.
[DYNAMIC_EXECUTION]: The skill utilizes the browser_eval tool to execute JavaScript logic within the Electron application's browser context, which is the intended mechanism for performing UI automation tasks like simulating user input and clicking buttons.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for reading state from the browser DOM (e.g., document.body.innerText), which creates an ingestion point for untrusted data. If the application renders external content, that content could contain instructions aimed at influencing the agent's behavior. The provided instructions do not specify the use of boundary markers or sanitization for this data.

browser-automation