The Agent Skills Directory

[COMMAND_EXECUTION]: The skill integrates automated accessibility testing by invoking industry-standard tools via the shell.
Evidence: The workflow utilizes npx @axe-core/cli and npx lighthouse to scan targeted URLs (e.g., http://localhost:8000). These are well-known tools for accessibility auditing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted content (HTML, JavaScript, and custom web components) to perform its core auditing function.
Ingestion points: The agent reads external web pages and source code during its "Audit Against WCAG Standards" and "Manual Assistive Technology Testing" phases.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded within the audited code (e.g., in HTML comments or ARIA labels).
Capability inventory: The skill has the ability to execute shell commands (npx) and interact with network resources to fetch audit data.
Sanitization: The instructions do not specify any sanitization, filtering, or escaping of the ingested content before the agent processes it.

accessibility-auditor