The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes external UI code and project files to perform accessibility audits, which creates an indirect prompt injection surface.
Ingestion points: The skill audits UI structures and code content (specifically focus indicators, headings, and ARIA usage) which are ingested into the agent context from the project files.
Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the code being audited and the agent's core instructions.
Capability inventory: The skill utilizes inspection-based tools and commands like grep and uiux_check_contrast. It does not demonstrate file-writing, network communication, or administrative execution capabilities.
Sanitization: No sanitization, validation, or escaping of the ingested code is mentioned before the agent processes it for analysis.

a11y-audit