chapter-skeleton
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The script dynamically resolves the repository root to import local tooling modules (tooling.common).
- [PROMPT_INJECTION]: The skill ingests data from outline/taxonomy.yml and GOAL.md without explicit sanitization or boundary markers, creating a surface for indirect prompt injection. The skill's capabilities are limited to writing YAML files.
Audit Metadata