The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official testing libraries including @playwright/test and @axe-core/playwright via the NPM registry, and references official GitHub Actions (actions/checkout, actions/setup-node) for CI/CD integration.
[COMMAND_EXECUTION]: Uses standard shell commands such as npx playwright test and npm init playwright@latest to manage test environments and execution.
[CREDENTIALS_UNSAFE]: Step 3 (Authentication Pattern) includes example credentials (test@example.com / password123) within the instructional code blocks to demonstrate how to handle authentication state.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection where untrusted data could influence agent behavior:
Ingestion points: Processes user prompts (e.g., 'test my login flow') to determine test logic and selectors in SKILL.md examples.
Boundary markers: Absent; there are no instructions to the agent to treat user-provided app descriptions or URLs as untrusted or to isolate them from the generated script context.
Capability inventory: The skill uses npx playwright test for execution and page.goto for browser navigation, which allows for local command execution and network operations.
Sanitization: Absent; the instructions do not include steps to sanitize user-provided strings before they are interpolated into test scripts or locators.

playwright-testing