skills/michaelmerrill/skills/scope/Gen Agent Trust Hub

scope

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the local project environment, managing project documentation in ./plans/ and reading from ./assets/ templates.
  • [SAFE]: No remote code execution, external downloads, or network exfiltration patterns are present in the instructions or templates.
  • [SAFE]: The 'Language barrier' rule explicitly instructs the agent to avoid surfacing technical identifiers (table names, file paths, technical abbreviations) to the user, providing a layer of abstraction that prevents unintended data exposure of codebase structure.
  • [SAFE]: The skill follows a standard multi-step logic (Domains 1-6) for project management without any attempts to bypass agent safety filters or override core instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 10:30 PM