The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions and checklists for UX auditing. It does not contain any executable scripts, shell commands, or automated tasks.
[INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion point for user-provided data via the $ARGUMENTS placeholder. While this represents a surface for indirect prompt injection (where a screen being audited might contain malicious instructions), the skill possesses no capabilities—such as file writing, network access, or command execution—that could be leveraged for an attack. The risk is effectively mitigated by the lack of functional tools.

ux-audit