breezing
Warn
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes extensive shell commands including git and mktemp to orchestrate workflows and manage task states.- [COMMAND_EXECUTION]: It delegates implementation tasks to the Codex CLI using the
--full-autoflag, allowing for automated code modification without user intervention.- [COMMAND_EXECUTION]: The skill explicitly configures sub-agents (Worker and Reviewer) withbypassPermissions. This setting suppresses standard platform security prompts, granting the agents elevated autonomy to execute commands and modify the file system without explicit user approval.
Audit Metadata