The Agent Skills Directory

[COMMAND_EXECUTION]: The SKILL.md file includes a Playwright configuration snippet that uses the webServer.command property to run npm run dev. This is a documented and standard method for starting a local development server for testing purposes.
[INDIRECT_PROMPT_INJECTION]: The skill documents browser automation tasks which represent an attack surface for indirect prompt injection should the agent navigate to malicious or untrusted websites.
Ingestion points: page.goto() methods described in SKILL.md allow the agent to load external content into the browser context.
Boundary markers: None are present in the provided examples to delimit external content from agent instructions.
Capability inventory: The skill utilizes subprocess execution (webServer.command) and file system operations (saving screenshots and reports) as part of its core functionality in SKILL.md.
Sanitization: No specific sanitization or filtering of web content is described in the snippets.

playwright-test