ux-audit-multidisciplinary
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's instructions are purely focused on establishing a multidisciplinary role-play persona for conducting design audits. It does not contain instructions to bypass safety filters or override core agent behavior.
- [SAFE]: While the skill involves reading local files (HTML and CSS) for technical analysis, it performs no network operations, data exfiltration, or credential harvesting.
- [NO_CODE]: The skill is entirely descriptive and instructional, containing no executable scripts, shell commands, or dynamic execution patterns.
- [SAFE]: The indirect prompt injection surface is minimal. Although the skill processes external data (DOM and CSS structure), it lacks the capabilities (like shell access or network requests) that could be exploited via malicious content in those files.
Audit Metadata