The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided HTML and component code, which serves as an ingestion point for potentially untrusted data.
Ingestion points: Rendered HTML and interactive design patterns referenced in SKILL.md.
Boundary markers: No specific delimiters are mandated for the user-provided code blocks.
Capability inventory: The skill does not define any executable tools, shell commands, or network operations; its output is restricted to text-based guidance.
Sanitization: There is no explicit sanitization logic for input data.
[SAFE]: The skill consists entirely of markdown documentation and code examples for accessibility best practices. All external links point to the official Frontend Checklist website, which is a recognized industry resource. No automated execution or data exfiltration vectors were identified.

accessible-tables