levelup-publish
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local setup scripts (
scripts/bash/setup-levelup-publish.shorscripts/powershell/setup-levelup-publish.ps1) to resolve project roots, verify repository configurations, and identify accepted CDR drafts. - [COMMAND_EXECUTION]: Automates standard Git operations including repository initialization, branch management, committing changes, and pushing to remote origins within the
team-ai-directivesdirectory. - [COMMAND_EXECUTION]: Utilizes the GitHub CLI (
gh) to programmatically create draft Pull Requests for the generated artifacts, facilitating a manual review process. - [SAFE]: Processes data from local CDR draft files to generate Markdown and JSON artifacts. This behavior is the primary purpose of the skill, and risks are mitigated by the creation of draft PRs which require human intervention before merging.
- [SAFE]: The skill instructions include a 'Signal Gate Validation' phase (Phase 2) and 'Cross-CDR Conflict Check' (Phase 3) which act as internal logic gates to ensure only high-quality, non-conflicting data is processed.
Audit Metadata