The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @playwright/mcp package via npx. This is an official package from the Playwright project, which is a well-known and reputable service.
[COMMAND_EXECUTION]: Includes the use of browser_evaluate, which executes JavaScript within the browser environment. This is a core functionality of the browser automation tool for tasks like checking page state.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes data from external websites (via browser_snapshot).
Ingestion points: Data enters the agent's context from external URLs via browser_navigate and browser_snapshot tools.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the processed web content.
Capability inventory: The agent has the ability to execute code in the browser (browser_evaluate), click elements, and fill forms, which could be targeted by malicious site content.
Sanitization: There is no mention of sanitizing or filtering the content retrieved from web pages before it is processed by the agent.

browse