khe-ui-review
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a purely instructional auditing tool. It uses a structured checklist to identify common UI/UX mistakes (e.g.,
transition: all, missing accessibility labels, or unoptimized animations). - [SAFE]: No external network dependencies or remote scripts are executed. The
npxcommand in the README is for installing the skill itself via a standard platform mechanism. - [SAFE]: The skill explicitly instructs the agent to treat repository content as data, not instructions, which is a defensive measure against indirect prompt injection where a file being reviewed might try to hijack the agent's behavior.
- [SAFE]: No evidence of obfuscation, persistence, or credential access was found. All references are local markdown files containing design principles and guidelines.
Audit Metadata