The Agent Skills Directory

[SAFE]: The skill provides purely instructional content for UI/UX design, covering foundations like visual balance, hierarchy, and restraint. It does not contain any executable scripts, binaries, or system-level commands.
[SAFE]: No data exposure or exfiltration risks were identified. The skill does not attempt to access sensitive files (e.g., .ssh, .aws) or perform network operations to untrusted domains.
[SAFE]: No obfuscation techniques were detected. All content is written in plain-text markdown, and there are no instances of Base64 encoding, zero-width characters, or homoglyphs.
[SAFE]: The skill does not install any external packages or download remote code. It references local reference files and existing platform tools (e.g., playwright-interactive-sandbox) in a manner consistent with its stated purpose of UI verification.
[SAFE]: No prompt injection or behavior override patterns were found. The instructions are structured to guide the agent's output format and design choices rather than bypassing safety filters or overriding system instructions.
[SAFE]: The skill involves processing external data (such as brand colors from DOMAIN.md), which technically represents a surface for indirect prompt injection. However, the risk is negligible as the agent is instructed to extract specific visual properties rather than execute content from those sources.

design-taste