hypothesis

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and templates in Korean. It does not utilize any external tools, perform network requests, or access the file system.
  • [SAFE]: No evidence of prompt injection, obfuscation, or malicious redirection was found. All instructions are consistent with the stated purpose of assisting a product design team.
  • [SAFE]: The skill mentions internal vendor services ('Allra-Fintech'), which is consistent with the provided author context and does not pose a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 06:52 AM