skills/clerk/javascript/mosaic/Gen Agent Trust Hub

mosaic

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists purely of Markdown documentation files providing guidance on a React-based UI architecture (machine -> controller -> view). There is no executable code or scripts provided within the skill files.
  • [SAFE]: All external references and packages mentioned, such as @clerk/headless, @clerk/ui, and @stylexjs/stylex, are standard development dependencies consistent with the stated purpose of the skill and the author's identity.
  • [SAFE]: The 'subagent prompt' provided in references/parity-audit.md is a template for a legitimate code audit task. It does not contain instructions to override safety filters or exfiltrate data; it provides a structured way for a secondary agent to compare code versions for behavioral parity.
  • [SAFE]: Shell commands provided (such as rg in migration.md) are standard developer utilities used for auditing source code patterns and do not involve privilege escalation or dangerous network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 03:18 AM
Security Audit — agent-trust-hub — mosaic