plan

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and defines a restrictive 'Plan Mode'. It explicitly forbids implementing code, editing project files (except for generated plans), running mutating terminal commands, and performing external actions.- [SAFE]: The restricted scope limits file writes to the .hermes/plans/ directory and mandates the use of read-only tools for repository inspection, ensuring no unauthorized data modification or exfiltration occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:01 PM
Security Audit — agent-trust-hub — plan