skills/dereknex/skills/ui-design-tips/Gen Agent Trust Hub

ui-design-tips

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local files or perform any network requests. It operates entirely on a local dataset.
  • [Remote Code Execution] (SAFE): No scripts, external dependencies, or dynamic code execution patterns were detected. The skill consists only of markdown instructions and a metadata JSON file.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process user UI descriptions and match them against a local JSON file (references/ui-design-tips.json). While the skill processes untrusted user input, it lacks the dangerous capabilities (such as file writing, shell execution, or network access) required to turn an injection into a high-impact attack.
  • [Obfuscation] (SAFE): No encoded strings, homoglyphs, or hidden characters were found in the provided files.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 12:39 PM