get-tasks

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates primarily as a document generator and project management tool. It reads existing documentation (PRDs) and produces Markdown task files and implementation plans within the tasks/ directory.
  • [SAFE]: The skill contains explicit safety constraints, such as the 'Planning is read-only' rule, which strictly prohibits the agent from creating, editing, or deleting source files during the breakdown phases (Phases 0-7). Writing task files is the only permitted filesystem change.
  • [SAFE]: Analysis of the instructions shows no evidence of prompt injection, credential harvesting, or obfuscation. The skill's logic is transparent and focuses on mapping dependencies and vertical slicing.
  • [SAFE]: The skill includes instructions for 'Replanning When a Task Fails', which maintains project integrity by ensuring that new dependencies or plan changes are documented rather than silently executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 07:31 AM