The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill audits external code or content for accessibility compliance, which serves as an ingestion point for untrusted data. Malicious instructions could potentially be hidden in the code being audited, such as within HTML comments or ARIA metadata. While the skill lack explicit boundary markers or sanitization instructions, this is a standard risk for auditing tasks rather than a direct vulnerability in the skill itself.
[SAFE]: The skill is purely instructional and contains no executable code, shell commands, or network operations. All referenced dependencies (axe, lighthouse) are standard industry tools for the stated purpose of accessibility auditing.

accessibility-checker