The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references standard packages from the official NPM registry, including @axe-core/playwright, axe-core, and playwright. These are well-known and trusted tools for web automation and accessibility testing.\n- [COMMAND_EXECUTION]: Provides standard npm install commands for developer environment setup, consistent with the skill's purpose and following best practices for software development.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing external web content during testing.\n
Ingestion points: The skill uses page.goto() to load external URLs and page.evaluate() to extract content from the browser's DOM (e.g., in SKILL.md).\n
Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are present to prevent the agent from being influenced by instructions discovered on tested pages.\n
Capability inventory: The skill utilizes Playwright, which allows for complex browser interaction, network requests, and interaction with the host environment through its test runner.\n
Sanitization: No explicit sanitization or filtering of the extracted web content is observed before it is processed by the analysis logic.

Axe-core Accessibility Testing