ux-expert

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata defining a persona. No executable scripts, binaries, or code snippets are provided within the skill files.
  • [SAFE]: No network operations (curl, wget, etc.), sensitive file system access, or credential usage were detected in the instructions.
  • [SAFE]: The skill describes an interaction workflow involving user input to generate documentation. While this represents a surface for user-provided data, the skill contains no dangerous capabilities (like code execution or file writing) that could be exploited via indirect prompt injection.
  • [SAFE]: References to external design tools (v0, Lovable) and other agent skills (create-frontend-spec, generate-ui-prompt) are purely descriptive and do not involve automated execution of untrusted remote resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:22 PM
Security Audit — agent-trust-hub — ux-expert