The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/check.py utilizes the Playwright library to spawn and control headless browser processes (Chromium and WebKit). This execution is central to the skill's primary function of rendering and inspecting web pages.
[EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of standard, well-known libraries playwright and pillow via the official Python package registry. Additionally, it requires downloading browser binaries from Playwright's official distribution channels.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from external URLs, which represents a potential attack surface if those pages contain malicious instructions intended for the agent.
Ingestion points: The target website's content is ingested via page.goto() within scripts/check.py.
Boundary markers: The skill relies on standard browser sandboxing; there are no specific markers to delineate untrusted page content within the automation logs or reports.
Capability inventory: The script can execute JavaScript on the page (page.evaluate), capture screenshots, and write performance reports to the local filesystem (report.json).
Sanitization: The skill does not perform content sanitization or filtering on the target website's text before including it in the report or console output.

site-check