herbert

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and reference data to establish a specific AI persona (Frank Herbert). There are no executable scripts or command-line instructions.
  • [SAFE]: The skill utilizes the 'Read' tool to load a shared configuration file ('../../framework.md') and a local personality reference ('reference.md'). This is a standard architectural pattern for organizing persona-based AI behaviors.
  • [SAFE]: No sensitive data exposure, prompt injection attempts, or obfuscated content were detected within the analyzed files.
  • [SAFE]: The skill's capabilities are strictly limited to reading its own configuration and interacting with the user via dialogue.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:05 PM
Security Audit — agent-trust-hub — herbert