skills/brianoneil/rocky-skills/rocky/Gen Agent Trust Hub

rocky

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not include any scripts, external dependencies, or commands.
  • [SAFE]: No data exfiltration or credential access patterns were detected. The skill focuses solely on modifying the output style of the agent.
  • [SAFE]: The instructions include a safety-conscious 'Auto-Clarity' rule, which mandates reverting to standard prose for security warnings and irreversible actions, demonstrating a security-positive design.
  • [SAFE]: No prompt injection, obfuscation, or persistence mechanisms were found. The 'Rocky mode' is a benign persona intended for efficiency.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 02:53 PM