The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the @playwright/mcp package from the official npm registry during installation and references documentation from Microsoft's public repositories.
[COMMAND_EXECUTION]: Provides an interface for executing browser automation commands. This includes a run-code command that allows the agent to execute arbitrary JavaScript snippets within the browser context to perform complex tasks or data extraction.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to process content from external, untrusted websites.
Ingestion points: Untrusted content enters the agent's context through commands like playwright-cli open <url>, snapshot, and console (which reads log messages from the page).
Boundary markers: The instructions do not define specific delimiters or security headers to separate untrusted web content from the agent's core instructions.
Capability inventory: The agent has significant capabilities including full browser control, network navigation, file generation (PDF/Screenshots), and JavaScript execution via the run-code utility.
Sanitization: No explicit sanitization or filtering of the ingested HTML or console data is performed before it is presented to the agent.

playwright-cli