The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @playwright/mcp package from the NPM registry and the subsequent download of browser binaries (such as Chromium) using the npx playwright install command. These resources are provided by well-known software providers and are used for their intended purpose.
[PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the web, which creates a surface for indirect prompt injection attacks.
Ingestion points: Tools such as browser_get_text, browser_snapshot, and browser_evaluate retrieve content directly from the DOM of navigated websites and feed it into the agent's context.
Boundary markers: The instructions do not define specific delimiters or "ignore" directives to help the agent distinguish between its own system prompt and potentially malicious instructions embedded in the retrieved web content.
Capability inventory: The skill provides high-privilege interaction tools, including browser_click, browser_type, and browser_evaluate (arbitrary JavaScript execution), which could be misused if the agent obeys an injected command from a malicious website.
Sanitization: There is no evidence of content sanitization or validation performed on the extracted text before it is presented to the agent.

playwright-mcp