skills/ironyjk/howtotalk/never-split/Gen Agent Trust Hub

never-split

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No prompt injection or behavior override patterns detected. The instructions are purely educational and provide structured templates for the agent's output.
  • [SAFE]: No sensitive data exposure or exfiltration patterns were found. Network access is restricted to legitimate references for the Black Swan Group (Chris Voss's official site).
  • [SAFE]: No obfuscation techniques, hidden characters, or homoglyph attacks were detected. The use of Korean terminology is contextual and for educational purposes.
  • [SAFE]: No remote code execution or unauthorized dependency installations were found.
  • [SAFE]: The skill uses allowed tools (Bash, WebSearch) in a standard manner for research and document management without signs of privilege escalation or persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 03:28 AM