NYC
skills/smithery/ai/ux-evaluator/Gen Agent Trust Hub

ux-evaluator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • PROMPT_INJECTION (SAFE): No instructions to bypass safety filters or override system prompts were found. The language is purely instructional for UX evaluation.
  • DATA_EXFILTRATION (SAFE): No commands for accessing sensitive files (e.g., .ssh, .aws) or making network requests (e.g., curl, wget) are present.
  • REMOTE_CODE_EXECUTION (SAFE): No remote downloads or execution patterns (e.g., curl | bash) were detected.
  • OBFUSCATION (SAFE): The content is clear markdown. No Base64, zero-width characters, or encoded strings were found.
  • PRIVILEGE_ESCALATION (SAFE): No use of sudo, chmod, or administrative commands.
  • INDIRECT_PROMPT_INJECTION (LOW): While the skill processes user-provided UI descriptions and external references, it lacks executable capabilities (file write, network, shell access), limiting the risk to purely informational context influence.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 08:29 AM