ux-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of 31 markdown files (SKILL.md and 30 law reference files). No Python scripts, JavaScript files, shell scripts, or binaries are included.
  • [EXTERNAL_DOWNLOADS] (SAFE): While the skill instructions permit the agent to fetch external links from 'Further Reading' sections, these URLs point to reputable educational and research domains such as nngroup.com, interaction-design.org, and smashingmagazine.com. These are intended for information retrieval only and do not involve downloading executable packages or scripts.
  • [PROMPT_INJECTION] (SAFE): The instructions in SKILL.md are well-structured for context-based advice. There are no attempts to override the agent's core safety guidelines, extract system prompts, or utilize role-play/DAN injection techniques.
  • [DATA_EXFILTRATION] (SAFE): There are no network operations, hardcoded credentials, or instructions to access sensitive system files (e.g., SSH keys, environment variables).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM