The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes Python scripts (scripts/ux_audit.py and scripts/accessibility_checker.py) intended for local project audits. These scripts perform static analysis using regular expressions to detect design patterns and accessibility issues and do not execute external code or commands.
[DATA_EXPOSURE]: The audit scripts access and read the contents of local project files (HTML, JSX, TSX) to perform design and accessibility reviews. This access is limited to the local filesystem and no evidence of data exfiltration or network activity was found.
[PROMPT_INJECTION]: The instructions include strong behavioral and stylistic constraints (e.g., 'PURPLE BAN' and 'Anti-Safe Harbor' rules) designed to prevent the AI from defaulting to generic design patterns. These are persona-alignment constraints and do not represent malicious injection attempts.

frontend-design