tell-me-first

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and designed to enhance safety by implementing a confirmation gateway. It explicitly forbids the agent from running commands, calling tools, or modifying files until a specific confirmation is received from the user. It does not request access to sensitive data or external resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:42 AM
Security Audit — agent-trust-hub — tell-me-first