skills/jayden-dang/skills/speak-outer/Gen Agent Trust Hub

speak-outer

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists entirely of natural language instructions and evaluation criteria for formatting AI agent responses to be more human-readable. It does not utilize any tools, perform network operations, access sensitive files, or execute code. The provided instructions and tests are focused on prompt engineering to ensure the agent uses an 'outer register' when interacting with human users.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:39 AM
Security Audit — agent-trust-hub — speak-outer