The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The implementation playbook references several well-known Node.js packages for accessibility testing, including puppeteer, @axe-core/puppeteer, jest-axe, and pa11y. It also utilizes official GitHub Actions such as actions/checkout and actions/setup-node in its CI/CD templates.
[COMMAND_EXECUTION]: The skill provides a GitHub Actions configuration file that executes standard shell commands for environment setup and test automation (npm ci, npm run build, npm start).
[SAFE]: The skill uses page.evaluate within a Puppeteer instance to analyze the Document Object Model (DOM) for accessibility violations. This behavior is standard and necessary for the stated purpose of auditing web interfaces.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) because it retrieves and processes content from external URLs provided by the user.
Ingestion points: The url argument passed to the runFullAudit method in resources/implementation-playbook.md.
Boundary markers: Absent; the skill does not use specific delimiters to separate user data from instructions when analyzing page content.
Capability inventory: The skill utilizes Puppeteer (page.goto, page.evaluate), granting it the ability to browse the web and execute scripts in a browser context.
Sanitization: Absent; the skill does not filter or sanitize the content of the target website before processing it.

accessibility-compliance-accessibility-audit