The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the agent-browser CLI tool to perform automated UI testing and scenario validation on provided URLs.
[EXTERNAL_DOWNLOADS]: The skill references an installation process that downloads the agent-browser package from the NPM registry and subsequently downloads the Chromium browser. The process correctly utilizes the AskQuestion tool to seek explicit user consent before performing any installations.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks. It ingests untrusted data by browsing external URLs provided by the user. If a reviewed website contains malicious instructions (e.g., hidden in HTML comments or page text), the agent might attempt to follow those instructions instead of its original goal. The skill lacks explicit boundary markers or sanitization logic to mitigate this runtime risk.

review-ui