skills/uucz/moyu/moyu-ko/Gen Agent Trust Hub

moyu-ko

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional text designed to refine the agent's behavior towards minimalist coding practices and adherence to user-specified scopes.
  • [SAFE]: No executable code, binary files, or external script downloads are present in the analyzed content.
  • [SAFE]: No patterns associated with credential harvesting, sensitive file access, or data exfiltration were detected.
  • [PROMPT_INJECTION]: The skill employs persona-based role-play (Staff Engineer) to steer the agent's output style. These instructions are standard behavioral alignment prompts and do not aim to bypass safety filters or extract system information.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 12:57 PM