The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for using the chrome-use CLI via bash to perform browser automation tasks, such as opening URLs, interacting with page elements, and managing background session daemons.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and execute the chrome-use package from the NPM registry. This is the primary tool for the skill's functionality.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it navigates to and processes content from external websites, which could contain instructions intended to influence the agent's behavior.
Ingestion points: Browser navigation and interaction via chrome-use open, chrome-use fill, and chrome-use tab list in SKILL.md.
Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are provided in the skill content.
Capability inventory: The skill possesses extensive browser control (click, type, eval, screenshot) and system process management (daemon restart) capabilities via bash.
Sanitization: No specific sanitization or filtering of external web content is described in the instructions.

sessions